From 9f2168b39042f417c3c78e9b76175666373041c9 Mon Sep 17 00:00:00 2001 From: Kaiyu Zheng Date: Tue, 25 Jul 2023 08:49:33 -0400 Subject: [PATCH] update docs accordingly --- CHANGELOG.rst | 1 + docs/html/_sources/changelog.rst.txt | 1 + docs/html/changelog.html | 1 + docs/html/problems/pomdp_problems.tiger.cythonize.html | 2 +- docs/html/searchindex.js | 2 +- 5 files changed, 5 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.rst b/CHANGELOG.rst index ea67f799..28699ddf 100644 --- a/CHANGELOG.rst +++ b/CHANGELOG.rst @@ -5,6 +5,7 @@ Best viewed on `the website Version 1.3.3 (07/25/2023) ------------------------- +* Bumped minimum Python requirement from 3.7 to 3.8 due to `EOL of 3.7 `_. * Fix :code:`cpdef -> cdef` to avoid installation failure after Cython 3.0.0 release (`pomdp-py#30 `_). * Added float_precision argument to to_pomdp_file (`pomdp-py#29 `_) * Add :code:`__init__` signature for Environment in comments to be visible in docs diff --git a/docs/html/_sources/changelog.rst.txt b/docs/html/_sources/changelog.rst.txt index ea67f799..28699ddf 100644 --- a/docs/html/_sources/changelog.rst.txt +++ b/docs/html/_sources/changelog.rst.txt @@ -5,6 +5,7 @@ Best viewed on `the website Version 1.3.3 (07/25/2023) ------------------------- +* Bumped minimum Python requirement from 3.7 to 3.8 due to `EOL of 3.7 `_. * Fix :code:`cpdef -> cdef` to avoid installation failure after Cython 3.0.0 release (`pomdp-py#30 `_). * Added float_precision argument to to_pomdp_file (`pomdp-py#29 `_) * Add :code:`__init__` signature for Environment in comments to be visible in docs diff --git a/docs/html/changelog.html b/docs/html/changelog.html index 64db608c..93e16a16 100644 --- a/docs/html/changelog.html +++ b/docs/html/changelog.html @@ -166,6 +166,7 @@

Changelog

Version 1.3.3 (07/25/2023)

    +

  • Bumped minimum Python requirement from 3.7 to 3.8 due to EOL of 3.7.

  • Fix cpdef -> cdef to avoid installation failure after Cython 3.0.0 release (pomdp-py#30).

  • Added float_precision argument to to_pomdp_file (pomdp-py#29)

  • Add __init__ signature for Environment in comments to be visible in docs

    • diff --git a/docs/html/problems/pomdp_problems.tiger.cythonize.html b/docs/html/problems/pomdp_problems.tiger.cythonize.html index 53e9e9ea..a3ff6850 100644 --- a/docs/html/problems/pomdp_problems.tiger.cythonize.html +++ b/docs/html/problems/pomdp_problems.tiger.cythonize.html @@ -398,7 +398,7 @@

    pomdp_problems.tiger.cythonize.tiger_problem.cpython-38-x86_64-linux-gnu mod

    Bases: POMDP

    -ACTIONS = {TigerAction(open-right), TigerAction(listen), TigerAction(open-left)}
    +ACTIONS = {TigerAction(open-right), TigerAction(open-left), TigerAction(listen)}
    diff --git a/docs/html/searchindex.js b/docs/html/searchindex.js index 045f0c1f..460a3c98 100644 --- a/docs/html/searchindex.js +++ b/docs/html/searchindex.js @@ -1 +1 @@ -Search.setIndex({"docnames": ["api/modules", "api/pomdp_py", "api/pomdp_py.algorithms", "api/pomdp_py.algorithms.bsp", "api/pomdp_py.algorithms.visual", "api/pomdp_py.framework", "api/pomdp_py.representations", "api/pomdp_py.representations.belief", "api/pomdp_py.representations.distribution", "api/pomdp_py.utils", "api/pomdp_py.utils.debugging", "api/pomdp_py.utils.interfaces", "api/pomdp_py.visual", "building_docs", "changelog", "design_principles", "examples", "examples.action_prior", "examples.external_solvers", "examples.mos", "examples.tiger", "existing_domains", "existing_solvers", "extensions", "index", "installation", "modules", "other_libraries", "problems/modules", "problems/pomdp_problems", "problems/pomdp_problems.lasertag", "problems/pomdp_problems.light_dark", "problems/pomdp_problems.light_dark.agent", "problems/pomdp_problems.light_dark.domain", "problems/pomdp_problems.light_dark.env", "problems/pomdp_problems.light_dark.models", "problems/pomdp_problems.load_unload", "problems/pomdp_problems.maze", "problems/pomdp_problems.maze.domain", "problems/pomdp_problems.maze.env", "problems/pomdp_problems.maze.models", "problems/pomdp_problems.maze.models.components", "problems/pomdp_problems.multi_object_search", "problems/pomdp_problems.multi_object_search.agent", "problems/pomdp_problems.multi_object_search.domain", "problems/pomdp_problems.multi_object_search.env", "problems/pomdp_problems.multi_object_search.models", "problems/pomdp_problems.multi_object_search.models.components", "problems/pomdp_problems.rocksample", "problems/pomdp_problems.rocksample.cythonize", "problems/pomdp_problems.tag", "problems/pomdp_problems.tag.agent", "problems/pomdp_problems.tag.domain", "problems/pomdp_problems.tag.env", "problems/pomdp_problems.tag.models", "problems/pomdp_problems.tag.models.components", "problems/pomdp_problems.tiger", "problems/pomdp_problems.tiger.cythonize", "simple_rl_integration"], "filenames": ["api/modules.rst", "api/pomdp_py.rst", "api/pomdp_py.algorithms.rst", "api/pomdp_py.algorithms.bsp.rst", "api/pomdp_py.algorithms.visual.rst", "api/pomdp_py.framework.rst", "api/pomdp_py.representations.rst", "api/pomdp_py.representations.belief.rst", "api/pomdp_py.representations.distribution.rst", "api/pomdp_py.utils.rst", "api/pomdp_py.utils.debugging.rst", "api/pomdp_py.utils.interfaces.rst", "api/pomdp_py.visual.rst", "building_docs.rst", "changelog.rst", "design_principles.rst", "examples.rst", "examples.action_prior.rst", "examples.external_solvers.rst", "examples.mos.rst", "examples.tiger.rst", "existing_domains.rst", "existing_solvers.rst", "extensions.rst", "index.rst", "installation.rst", "modules.rst", "other_libraries.rst", "problems/modules.rst", "problems/pomdp_problems.rst", "problems/pomdp_problems.lasertag.rst", "problems/pomdp_problems.light_dark.rst", "problems/pomdp_problems.light_dark.agent.rst", "problems/pomdp_problems.light_dark.domain.rst", "problems/pomdp_problems.light_dark.env.rst", "problems/pomdp_problems.light_dark.models.rst", "problems/pomdp_problems.load_unload.rst", "problems/pomdp_problems.maze.rst", "problems/pomdp_problems.maze.domain.rst", "problems/pomdp_problems.maze.env.rst", "problems/pomdp_problems.maze.models.rst", "problems/pomdp_problems.maze.models.components.rst", "problems/pomdp_problems.multi_object_search.rst", "problems/pomdp_problems.multi_object_search.agent.rst", "problems/pomdp_problems.multi_object_search.domain.rst", "problems/pomdp_problems.multi_object_search.env.rst", "problems/pomdp_problems.multi_object_search.models.rst", "problems/pomdp_problems.multi_object_search.models.components.rst", "problems/pomdp_problems.rocksample.rst", "problems/pomdp_problems.rocksample.cythonize.rst", "problems/pomdp_problems.tag.rst", "problems/pomdp_problems.tag.agent.rst", "problems/pomdp_problems.tag.domain.rst", "problems/pomdp_problems.tag.env.rst", "problems/pomdp_problems.tag.models.rst", "problems/pomdp_problems.tag.models.components.rst", "problems/pomdp_problems.tiger.rst", "problems/pomdp_problems.tiger.cythonize.rst", "simple_rl_integration.rst"], "titles": ["pomdp_py", "pomdp_py package", "pomdp_py.algorithms package", "pomdp_py.algorithms.bsp package", "pomdp_py.algorithms.visual package", "pomdp_py.framework package", "pomdp_py.representations package", "pomdp_py.representations.belief package", "pomdp_py.representations.distribution package", "pomdp_py.utils package", "pomdp_py.utils.debugging module", "pomdp_py.utils.interfaces package", "pomdp_py.visual package", "Building Documentations", "Changelog", "Design Principles", "Examples", "Preference-based Action Prior", "Using External Solvers", "Multi-Object Search (MOS)", "Tiger", "Existing POMDP Domains", "Existing POMDP Solvers", "Use Case Extensions", "pomdp_py Documentation", "Installation", "docs", "Other POMDP Libraries", "pomdp_problems", "pomdp_problems package", "pomdp_problems.lasertag package", "Light-Dark", "pomdp_problems.light_dark.agent package", "Submodules", "pomdp_problems.light_dark.env package", "pomdp_problems.light_dark.models package", "Load/Unload", "pomdp_problems.maze package", "pomdp_problems.maze.domain package", "pomdp_problems.maze.env package", "pomdp_problems.maze.models package", "pomdp_problems.maze.models.components package", "Multi-Object Search (MOS) Task", "pomdp_problems.multi_object_search.agent package", "pomdp_problems.multi_object_search.domain package", "pomdp_problems.multi_object_search.env package", "pomdp_problems.multi_object_search.models package", "pomdp_problems.multi_object_search.models.components package", "RockSample", "pomdp_problems.rocksample.cythonize package", "Tag", "pomdp_problems.tag.agent package", "pomdp_problems.tag.domain package", "pomdp_problems.tag.env package", "pomdp_problems.tag.models package", "pomdp_problems.tag.models.components package", "Tiger", "pomdp_problems.tiger.cythonize package", "Integration with simple_rl"], "terms": {"packag": [0, 13, 19, 21, 24, 25, 28, 31, 42, 48, 50, 56], "algorithm": [0, 1, 5, 14, 18, 23, 24, 27, 31, 50], "po_rollout": [0, 1], "modul": [0, 1, 6, 13, 14, 19, 20, 24, 28, 29], "porollout": [0, 1, 2], "po_uct": [0, 1], "actionprior": [0, 1, 2, 14, 17, 20], "pouct": [0, 1, 2, 9, 10, 14, 17, 19, 20, 22, 23, 42, 50], "qnode": [0, 1, 2, 9, 10], "randomrollout": [0, 1, 2, 36, 57], "rolloutpolici": [0, 1, 2, 9, 17, 20, 46, 48, 49, 54, 56], "rootvnod": [0, 1, 2], "treenod": [0, 1, 2], "vnode": [0, 1, 2, 9, 10, 14], "pomcp": [0, 1, 7, 9, 10, 14, 17, 20, 22, 23, 25, 27, 42], "rootvnodeparticl": [0, 1, 2], "vnodeparticl": [0, 1, 2], "value_iter": [0, 1], "valueiter": [0, 1, 2, 14, 20, 22], "bsp": [0, 1], "blqr": [0, 1, 14, 31], "visual": [0, 1, 19, 25, 31, 42, 50], "framework": [0, 1, 14, 15, 19, 20, 24, 36, 57], "basic": [0, 1, 2, 7, 15, 18, 20, 22, 48, 49], "action": [0, 1, 2, 5, 7, 9, 10, 12, 14, 15, 18, 19, 20, 22, 25, 28, 31, 35, 36, 42, 45, 46, 47, 48, 49, 50, 53, 54, 55, 56, 57], "agent": [0, 1, 2, 5, 7, 9, 10, 15, 19, 20, 21, 22, 23, 24, 25, 28, 31, 36, 37, 38, 42, 46, 47, 48, 49, 50, 52, 56, 57], "blackboxmodel": [0, 1, 5, 7, 14, 20], "distribut": [0, 1, 2, 5, 6, 7, 9, 15, 17, 20, 35, 36, 43, 46, 48, 49, 54, 56, 57], "environ": [0, 1, 5, 14, 15, 19, 20, 34, 39, 42, 45, 46, 53, 56, 57], "generativedistribut": [0, 1, 5, 8, 43, 55], "observ": [0, 1, 2, 3, 5, 7, 9, 10, 12, 14, 15, 18, 19, 20, 22, 24, 25, 28, 31, 34, 35, 36, 37, 42, 45, 46, 47, 48, 49, 50, 53, 54, 56, 57], "observationmodel": [0, 1, 5, 7, 9, 15, 20, 23, 28, 31, 35, 36, 46, 48, 49, 54, 56, 57], "option": [0, 1, 2, 5, 9, 10, 14, 18, 20, 44, 46, 47, 48, 49, 56, 57], "pomdp": [0, 1, 2, 5, 9, 10, 13, 14, 15, 16, 17, 23, 24, 31, 36, 37, 42, 44, 46, 48, 49, 50, 52, 53, 54, 56, 57], "policymodel": [0, 1, 2, 5, 14, 17, 20, 23, 28, 42, 46, 56], "rewardmodel": [0, 1, 5, 9, 14, 15, 20, 28, 36, 46, 48, 49, 54, 56, 57], "state": [0, 1, 2, 3, 5, 7, 8, 9, 14, 15, 17, 18, 19, 20, 22, 25, 27, 28, 31, 35, 36, 37, 42, 43, 45, 46, 48, 49, 50, 54, 56, 57], "transitionmodel": [0, 1, 5, 7, 9, 15, 20, 23, 28, 31, 35, 36, 46, 48, 49, 54, 56, 57], "sample_explict_model": [0, 1, 5], "sample_generative_model": [0, 1, 5], "oopomdp": [0, 1, 14, 19, 23, 42], "oobelief": [0, 1, 5, 14, 43, 45, 53], "ooobserv": [0, 1, 5, 44], "ooobservationmodel": [0, 1, 5, 46], "oostat": [0, 1, 5, 14, 44], "ootransitionmodel": [0, 1, 5, 46], "objectst": [0, 1, 5, 42, 44], "planner": [0, 1, 2, 3, 18, 20, 36, 42, 48, 49, 56, 57], "represent": [0, 1, 2, 5, 14, 24, 43, 45], "belief": [0, 1, 2, 3, 5, 6, 8, 14, 18, 19, 20, 25, 31, 33, 34, 35, 36, 42, 45, 48, 49, 51, 53, 56], "histogram": [0, 1, 6, 14, 18, 20, 42, 43, 57], "particl": [0, 1, 2, 6, 14, 25, 43], "gaussian": [0, 1, 2, 3, 6, 35], "util": [0, 1, 12, 14, 18, 24], "subpackag": [0, 1, 28, 29], "interfac": [0, 1, 5, 9, 14, 15, 18, 19, 20, 21, 22, 23, 24, 27], "submodul": [0, 1, 28, 29, 40], "color": [0, 1, 10, 45, 53], "lighter": [0, 1, 9], "rgb_to_hex": [0, 1, 9], "hex_to_rgb": [0, 1, 9], "inverse_color_rgb": [0, 1, 9], "inverse_color_hex": [0, 1, 9], "random_unique_color": [0, 1, 9], "cython_util": [0, 1], "cpython": [0, 1, 28, 29], "37m": [0, 1, 28, 29], "x86_64": [0, 1, 28, 29], "linux": [0, 1, 25, 28, 29], "gnu": [0, 1, 28, 29], "det_dict_hash": [0, 1, 9], "debug": [0, 1, 12, 14, 24], "treedebugg": [0, 1, 12, 14, 56], "sorted_by_str": [0, 1, 9, 10], "interpret_color": [0, 1, 9, 10], "math": [0, 1, 2, 5, 14, 35], "vec": [0, 1, 9], "proj": [0, 1, 9], "r_x": [0, 1, 9], "r_y": [0, 1, 9], "r_z": [0, 1, 9], "t": [0, 1, 2, 3, 5, 7, 8, 9, 15, 18, 20, 22, 27, 42, 43, 45, 56, 57], "to_radian": [0, 1, 9], "r_between": [0, 1, 9], "approx_equ": [0, 1, 9], "euclidean_dist": [0, 1, 9, 28, 47, 48, 49], "misc": [0, 1], "remap": [0, 1, 9], "json_saf": [0, 1, 9], "safe_slic": [0, 1, 9], "similar": [0, 1, 9, 18, 20], "special_char": [0, 1, 9], "plot": [0, 1, 25, 31, 34], "plot_point": [0, 1, 9], "save_plot": [0, 1, 9], "plot_polygon": [0, 1, 9], "plot_lin": [0, 1, 9], "plot_circl": [0, 1, 9], "templat": [0, 1, 14], "simplest": [0, 1, 9], "simpleact": [0, 1, 9], "simpleobserv": [0, 1, 9], "dettransitionmodel": [0, 1, 9], "detobservationmodel": [0, 1, 9], "detrewardmodel": [0, 1, 9], "uniformpolicymodel": [0, 1, 9], "tabulartransitionmodel": [0, 1, 9, 14], "tabularobservationmodel": [0, 1, 9, 14], "tabularrewardmodel": [0, 1, 9, 14], "test_util": [0, 1], "remove_fil": [0, 1, 9], "make_tig": [0, 1, 9], "typ": [0, 1], "bcolor": [0, 1, 9], "info": [0, 1, 9], "note": [0, 1, 2, 5, 7, 8, 9, 10, 17, 18, 20, 24, 25, 31, 42, 46, 56, 57], "error": [0, 1, 9, 14], "warn": [0, 1, 2, 9, 10, 18], "success": [0, 1, 2, 9], "bold": [0, 1, 9], "cyan": [0, 1, 9], "magenta": [0, 1, 9], "blue": [0, 1, 9, 10], "green": [0, 1, 9, 25], "yellow": [0, 1, 9], "red": [0, 1, 9, 19], "white": [0, 1, 9], "content": [0, 1, 13, 24, 28, 29, 50, 56], "clear_ag": [1, 2], "last_best_reward": [1, 2], "plan": [1, 2, 3, 5, 9, 10, 14, 17, 18, 20, 23, 24, 27, 31, 33, 34, 35, 42, 46, 47, 50, 56], "set_rollout_polici": [1, 2], "updat": [1, 2, 3, 5, 7, 9, 10, 14, 18, 19, 20, 42, 45, 50, 53], "update_agent_belief": [1, 2, 5], "get_preferred_act": [1, 2, 17], "last_num_sim": [1, 2, 20], "last_planning_tim": [1, 2], "updates_agent_belief": [1, 2, 5], "rollout": [1, 2, 9, 14, 17, 20, 42, 46, 48, 49, 50, 54, 56], "from_vnod": [1, 2], "histori": [1, 2, 5, 9, 10, 17, 20, 43, 46, 48, 49, 51, 54, 56], "children": [1, 2, 9, 10, 14], "num_visit": [1, 2], "valu": [1, 2, 5, 6, 8, 9, 10, 14, 17, 18, 20, 25, 27, 48, 49, 50, 55, 56], "argmax": [1, 2, 5, 9, 14, 20, 31, 35, 36, 42, 46, 48, 49, 50, 54, 56, 57], "print_children_valu": [1, 2], "ekf_update_mlo": [1, 2, 3], "integrate_belief_seg": [1, 2, 3], "segmented_cost_funct": [1, 2, 3], "create_plan": [1, 2, 3], "interpret_sqp_plan": [1, 2, 3], "add_attr": [1, 5], "all_act": [1, 5], "all_observ": [1, 5], "all_stat": [1, 5], "init_belief": [1, 5, 9, 20, 36, 48, 51, 56, 57], "sample_belief": [1, 5], "set_belief": [1, 5, 18, 20], "update_histori": [1, 5, 20], "sampl": [1, 2, 5, 8, 9, 14, 17, 18, 20, 25, 31, 35, 36, 42, 43, 46, 48, 49, 50, 54, 56, 57], "__getitem__": [1, 5, 6, 8, 9, 10], "__setitem__": [1, 5, 6, 8], "apply_transit": [1, 5], "blackbox_model": [1, 5, 7], "cur_stat": [1, 5], "provide_observ": [1, 5], "reward_model": [1, 5, 19, 20, 34, 42, 50], "state_transit": [1, 5, 18, 20, 42, 45], "transition_model": [1, 5, 7, 18, 19, 20, 31, 42, 50], "get_histogram": [1, 5, 6, 8], "mpe": [1, 5, 6, 8, 14, 43, 50, 54, 55], "get_all_observ": [1, 5, 9, 20, 56, 57], "get_distribut": [1, 5, 56, 57], "probabl": [1, 5, 8, 9, 14, 15, 18, 20, 22, 31, 35, 36, 37, 42, 43, 46, 48, 49, 50, 54, 55, 56, 57], "initi": [1, 5, 14, 17, 18, 19, 20, 31, 43, 45, 48, 49, 51, 56], "polici": [1, 2, 5, 9, 14, 17, 18, 20, 36, 37, 46, 48, 49, 54, 56, 57], "termin": [1, 2, 5, 9, 10, 18, 20, 42, 48, 49], "get_all_act": [1, 5, 9, 17, 20, 36, 42, 46, 48, 49, 50, 54, 56, 57], "get_all_st": [1, 5, 9, 20, 56, 57], "b": [1, 2, 3, 5, 7, 9, 10, 18], "object_belief": [1, 5, 43], "random": [1, 2, 5, 6, 8, 9, 14, 17, 20, 43, 46, 48, 49, 50, 54, 55], "set_object_belief": [1, 5], "factor": [1, 5, 18, 42, 44], "merg": [1, 5, 42, 44], "observation_model": [1, 5, 7, 18, 19, 20, 31, 42, 50, 53], "copi": [1, 5, 25], "get_object_attribut": [1, 5], "get_object_class": [1, 5], "get_object_st": [1, 5], "": [1, 2, 3, 5, 7, 9, 10, 13, 14, 15, 18, 20, 22, 24, 31, 35, 36, 37, 42, 44, 45, 46, 47, 48, 49, 52, 54, 56, 57], "set_object_st": [1, 5], "situat": [1, 5, 19], "abstraction_over_histogram": [1, 6, 7], "update_histogram_belief": [1, 6, 7, 18, 20], "abstraction_over_particl": [1, 6, 7], "particle_reinvigor": [1, 6, 7], "update_particles_belief": [1, 6, 7], "is_norm": [1, 6, 8], "add": [1, 2, 6, 8, 14, 43], "from_histogram": [1, 6, 8], "get_abstract": [1, 6, 8], "weightedparticl": [1, 6, 8, 14], "condens": [1, 6, 8], "weight": [1, 2, 6, 8, 9], "cov": [1, 6, 8], "covari": [1, 2, 3, 6, 8], "mean": [1, 2, 6, 7, 8, 18, 35, 45, 47, 50], "sigma": [1, 6, 8, 42, 43, 46], "simple_rl": [1, 9, 24, 27], "num_nod": [1, 9, 10], "depth": [1, 2, 9, 10, 12], "d": [1, 2, 3, 9, 10, 20, 24], "num_lay": [1, 9, 10], "nl": [1, 9, 10], "nn": [1, 9, 10], "nq": [1, 9, 10], "nv": [1, 9, 10], "l": [1, 2, 3, 9, 10, 19, 20, 24, 36], "layer": [1, 9, 10], "leaf": [1, 9, 10], "step": [1, 2, 9, 10, 13, 14, 18, 20, 25, 42, 56, 57], "back": [1, 9, 10], "root": [1, 9, 10, 12, 13, 25], "r": [1, 2, 3, 5, 9, 10, 14, 15, 18, 20, 22, 24, 25, 33, 36, 42, 45, 46, 48, 49, 50, 53, 54, 56, 57], "c": [1, 2, 9, 10, 27], "p": [1, 9, 10, 24, 48, 49], "pp": [1, 9, 10], "mbp": [1, 9, 10], "pm": [1, 9, 10], "mark_sequ": [1, 9, 10], "mark": [1, 9, 10, 19, 31, 37, 44], "mark_path": [1, 9, 10], "markp": [1, 9, 10], "clear": [1, 2, 9, 10, 19, 43, 51], "bestseq": [1, 9, 10], "bestseqd": [1, 9, 10], "single_node_str": [1, 9, 10], "preferred_act": [1, 9, 10], "path": [1, 9, 10, 13, 18, 34], "path_to": [1, 9, 10], "tree_stat": [1, 9, 10], "left": [1, 9, 10, 18, 20, 25, 36, 42, 44, 56, 57], "up": [1, 5, 9, 10, 12, 36], "right": [1, 9, 10, 18, 20, 25, 36, 42, 43, 44, 56, 57], "down": [1, 9, 20], "longleft": [1, 9], "longright": [1, 9], "hline": [1, 9], "vline": [1, 9], "bottomleft": [1, 9], "longbottomleft": [1, 9], "topleft": [1, 9], "longtopleft": [1, 9], "topright": [1, 9], "longtopright": [1, 9], "bottomright": [1, 9], "longbottomright": [1, 9], "intersect": [1, 9], "topt": [1, 9], "leftt": [1, 9], "rightt": [1, 9], "bottomt": [1, 9], "shadebar": [1, 9], "subscript": [1, 9], "reward_func": [1, 9], "endc": [1, 9], "disabl": [1, 9], "exist": [2, 9, 10, 16, 18, 20, 23, 24], "solver": [2, 14, 16, 19, 20, 24, 56], "under": [2, 13, 18, 20, 27, 47], "develop": [2, 5, 18, 22, 24, 25, 27], "contribut": [2, 21, 24, 25], "want": [2, 13, 19, 43], "po": [2, 24, 35, 48, 49], "baselin": 2, "paper": [2, 3, 17, 19, 20, 24, 31, 33, 35, 36, 37, 42, 44, 46, 52, 54], "2": [2, 9, 10, 17, 18, 20, 24, 25, 27, 33, 35, 36, 44, 48, 49, 50, 51, 53, 54, 55], "quot": [2, 20, 31, 33, 35, 36, 37, 56, 57], "from": [2, 5, 8, 9, 10, 13, 17, 18, 19, 20, 25, 31, 33, 35, 36, 37, 43, 44, 45, 46, 47, 51, 54, 56, 57], "To": [2, 9, 10, 13, 17, 19, 20, 36, 57], "provid": [2, 18, 19, 20, 23, 24, 27], "perform": [2, 3, 5, 18, 20, 27], "benchmark": 2, "case": [2, 7, 18, 20, 21, 24, 27, 42, 45, 46, 56, 57], "we": [2, 13, 16, 18, 19, 20, 21, 24, 25, 27, 31, 42, 43, 46, 47], "evalu": [2, 8], "simpl": [2, 16, 19, 20, 24, 31, 44, 46, 47, 48, 49, 50, 56], "mont": [2, 20], "carlo": [2, 20], "simul": [2, 5, 14, 18, 20, 42, 45, 56], "without": [2, 18, 19, 20], "ani": [2, 8, 18, 37, 45, 46], "tree": [2, 9, 10, 12, 14, 19, 20, 25], "The": [2, 3, 5, 8, 9, 10, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 27, 31, 33, 35, 36, 37, 38, 42, 44, 45, 46, 47, 48, 49, 50, 52, 54, 56, 57], "us": [2, 3, 5, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17, 19, 20, 21, 22, 24, 25, 27, 31, 35, 42, 43, 44, 45, 46, 47, 56], "describ": [2, 3, 5, 13, 15, 16, 17, 19, 20, 24, 42, 45], "section": [2, 19, 20], "3": [2, 9, 10, 18, 20, 25, 27, 36, 44, 45, 48, 49, 56, 57], "It": [2, 3, 5, 8, 9, 10, 14, 17, 18, 19, 20, 24, 27, 44, 46], "n": [2, 7, 8, 9, 10, 18, 19, 35, 42, 44, 48, 49], "A": [2, 3, 5, 9, 10, 14, 15, 18, 19, 20, 22, 24, 27, 31, 36, 37, 42, 43, 45, 51, 56, 57], "each": [2, 3, 5, 8, 9, 10, 18, 36, 37, 45, 46], "legal": 2, "select": 2, "highest": [2, 5, 8, 9, 10, 55], "averag": [2, 8], "return": [2, 3, 5, 7, 8, 9, 10, 14, 17, 18, 20, 35, 36, 43, 45, 46, 47, 48, 49, 54, 55, 56, 57], "don": [2, 5, 7, 20, 42], "requir": [2, 5, 7, 9, 15, 25, 36, 46, 48, 49, 54, 56, 57], "an": [2, 3, 5, 8, 9, 14, 15, 17, 18, 19, 20, 22, 24, 27, 31, 33, 35, 36, 37, 42, 43, 44, 45, 46, 47, 48, 49, 50, 53, 56, 57], "But": [2, 5, 7, 13, 14, 20, 42, 44, 46, 56, 57], "do": [2, 5, 13, 19, 20, 31], "class": [2, 3, 5, 8, 9, 10, 14, 15, 17, 18, 19, 20, 23, 31, 33, 34, 35, 36, 38, 39, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57], "base": [2, 3, 5, 7, 8, 9, 10, 13, 18, 19, 20, 23, 24, 27, 31, 33, 34, 35, 36, 38, 39, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57], "self": [2, 5, 8, 9, 10, 17, 19, 20, 35, 36, 43, 45, 46, 48, 49, 54, 55, 56, 57], "carri": [2, 5], "inform": [2, 3, 5, 13, 15, 20, 47, 51], "bt": [2, 3, 5, 35], "ht": [2, 5], "o": [2, 5, 7, 9, 13, 15, 18, 20, 22, 24, 36, 48, 49, 54, 56, 57], "g": [2, 3, 5, 14, 20, 21, 33, 35, 37, 42, 45, 56], "pi": [2, 5, 15, 20, 36, 46, 48, 49, 57], "necessari": [2, 5, 19, 42], "rollout_polici": [2, 9, 10, 20], "given": [2, 5, 7, 8, 9, 10, 12, 15, 17, 18, 20, 36, 42, 45, 46, 57], "one": [2, 5, 9, 10, 16, 20, 24, 27, 36, 43, 45, 56, 57], "real_act": [2, 5, 7, 42, 51], "real_observ": [2, 5, 7, 20, 42, 51], "real": [2, 5, 7, 18, 20, 42, 45, 53], "accordingli": [2, 5], "If": [2, 3, 5, 7, 8, 9, 10, 12, 18, 20, 24, 43, 45, 46, 51, 56, 57], "i": [2, 3, 5, 7, 8, 9, 10, 12, 13, 14, 15, 17, 18, 19, 20, 21, 24, 25, 27, 31, 33, 35, 36, 37, 38, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 56, 57], "also": [2, 5, 9, 10, 19, 20, 22, 24, 27, 56, 57], "here": [2, 5, 9, 10, 13, 17, 18, 20, 21, 25, 31], "attribut": [2, 5, 44], "should": [2, 3, 5, 7, 13, 14, 15, 18, 19, 20, 23, 25, 44, 46], "set": [2, 5, 7, 8, 9, 14, 17, 18, 19, 20, 27, 36, 43, 44, 45, 47, 48, 49, 54, 56, 57], "true": [2, 5, 7, 8, 9, 10, 12, 14, 18, 20, 25, 37, 42, 45, 46, 47, 50, 56], "By": [2, 5, 18, 47], "default": [2, 5, 7, 14, 18, 56], "doe": [2, 5, 8, 9, 10, 14, 15, 18, 20, 27, 37, 47, 54], "noth": [2, 5], "function": [2, 3, 5, 7, 8, 9, 10, 14, 17, 18, 20, 22, 31, 35, 42, 43, 45, 51], "thi": [2, 3, 5, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17, 18, 20, 24, 25, 27, 31, 34, 35, 36, 42, 43, 44, 45, 46, 47, 48, 49, 50, 53, 54, 56, 57], "uct": 2, "partial": [2, 20, 24, 36, 37, 56, 57], "present": [2, 8, 31], "extens": [2, 20, 21, 24, 27, 44, 46, 50], "combin": [2, 9, 12], "mct": [2, 25], "ucb1": [2, 14], "In": [2, 16, 17, 18, 19, 20, 21, 31, 42, 54, 56, 57], "other": [2, 20, 24, 48, 49, 56, 57], "word": 2, "just": [2, 8, 9, 18, 20, 25, 33, 38, 43, 56, 57], "arbitrari": 2, "strategi": 2, "mai": [2, 5, 7, 13, 15, 16, 19, 24, 25, 31, 42], "refer": [2, 3, 13, 14, 17, 31, 35, 48, 56, 57], "spars": 2, "poss": 2, "introduc": [2, 19, 20, 36, 37], "recent": 2, "5": [2, 3, 9, 10, 18, 20, 25, 35, 45, 47, 48, 49, 56], "mdp": [2, 5, 24, 27], "6": [2, 9, 10, 18, 20, 25, 50], "propos": 2, "call": [2, 5, 7, 18, 20], "powss": 2, "howev": [2, 20], "line": [2, 18, 19], "work": [2, 9, 10, 12, 14, 18, 20, 24, 25, 27], "sole": 2, "still": [2, 7, 20], "compar": [2, 8], "exactli": 2, "while": [2, 14, 20, 36, 56, 57], "depend": [2, 3, 5, 9, 14, 31, 35, 54], "explor": [2, 9, 10], "constant": [2, 9, 28, 29], "7": [2, 9, 10, 18], "reflect": 2, "prior": [2, 5, 14, 20, 42, 43, 50, 51, 56], "knowledg": [2, 20], "regard": [2, 5, 14, 20], "amount": [2, 31], "thei": [2, 7, 18, 43, 47], "follow": [2, 3, 5, 9, 10, 17, 18, 19, 20, 24, 25, 35, 42, 56, 57], "wa": [2, 14, 19], "r_": 2, "hi": 2, "lo": 2, "where": [2, 3, 5, 7, 9, 19, 20, 25, 31, 35, 42, 44, 45, 46, 48, 49], "rhi": 2, "achiev": 2, "dure": [2, 9, 10, 14, 17, 18, 20, 47], "run": [2, 13, 14, 18, 19, 20, 25, 47, 56, 57], "0": [2, 5, 8, 9, 10, 17, 18, 20, 25, 34, 35, 36, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 53, 54, 55, 56], "rlo": 2, "lowest": 2, "inde": [2, 20], "differ": [2, 13, 14, 15, 19, 27, 36, 42, 44, 46], "between": [2, 5, 9, 14, 15, 19, 27, 36, 45, 47, 56], "certainli": 2, "onli": [2, 5, 9, 10, 12, 14, 15, 20, 37, 46, 56], "wai": [2, 18, 20, 27], "obtainx1": 2, "object": [2, 5, 9, 10, 14, 17, 20, 23, 24, 25, 28, 29, 34, 43, 44, 45, 46, 47, 48, 49, 53, 55], "problem": [2, 3, 5, 7, 13, 16, 18, 20, 21, 24, 25, 27, 28, 29, 31, 33, 36, 37, 38, 43, 45, 48, 49, 52, 54, 56, 57], "specif": [2, 5, 8, 9, 10, 14, 20, 27], "cl": [2, 5], "kwarg": [2, 5, 8, 9, 10, 14, 35, 36, 43, 44, 45, 46, 48, 49, 50, 53, 55, 57], "intend": 2, "classmethod": [2, 5, 8, 18, 44, 46, 53, 54, 55], "mimic": 2, "behavior": [2, 14, 20, 44], "generateleg": 2, "generatepref": 2, "david": [2, 20], "silver": [2, 20], "code": [2, 5, 9, 14, 17, 18, 19, 20, 24, 27], "tupl": [2, 3, 5, 8, 9, 43, 45, 46, 48, 49, 54], "form": [2, 7], "num_visits_init": 2, "value_init": 2, "repres": [2, 3, 5, 7, 8, 9, 10, 16, 18, 19, 43, 48, 49], "prefer": [2, 9, 10, 14, 20], "act": [2, 5, 20, 24, 25, 56], "despot": [2, 27, 50], "For": [2, 5, 8, 12, 14, 20, 25, 45, 47, 50], "exampl": [2, 5, 9, 10, 14, 17, 19, 20, 21, 22, 24, 42, 45, 47, 56, 57], "certain": [2, 5], "possibl": [2, 5, 9, 20, 27, 36, 44, 46, 48, 49, 54, 56, 57], "subset": [2, 9, 10], "all": [2, 5, 8, 9, 10, 14, 20, 27, 35, 36, 43, 46, 48, 49, 54, 56, 57], "when": [2, 5, 8, 9, 10, 13, 14, 16, 17, 18, 19, 20, 24, 25, 27, 42, 48, 49, 52, 54], "domain": [2, 9, 14, 16, 19, 24, 28, 31, 34, 35, 42, 46, 48, 50, 56], "can": [2, 5, 9, 10, 14, 18, 19, 20, 22, 25, 27, 31, 36, 38, 42, 44, 45, 46, 52, 56, 57], "heurist": [2, 20, 48, 49], "space": [2, 3, 5, 7, 14, 18, 19, 20, 22, 31, 33, 34, 35, 36, 37, 43, 44, 46, 48, 49, 52, 56, 57], "enumer": [2, 9, 10, 14, 15, 18, 20, 22, 56], "__init__": [2, 5, 8, 13, 14, 17, 19, 20], "max_depth": [2, 9, 10, 12, 20, 42, 50], "planning_tim": [2, 14, 20, 42, 50], "1": [2, 3, 5, 8, 9, 10, 12, 17, 18, 19, 20, 24, 25, 31, 34, 35, 36, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 53, 54, 56, 57], "num_sim": [2, 9, 10, 14], "discount_factor": [2, 5, 9, 10, 18, 20, 42, 50], "9": [2, 9, 14, 18, 20, 25], "exploration_const": [2, 9, 10, 20, 42, 50], "sqrt": 2, "action_prior": [2, 17], "none": [2, 3, 5, 7, 8, 9, 10, 12, 17, 18, 20, 25, 34, 42, 43, 44, 46, 48, 49, 53, 54, 56], "show_progress": 2, "fals": [2, 5, 7, 9, 12, 18, 25, 33, 35, 36, 42, 43, 45, 46, 47, 48, 49, 53, 55, 56, 57], "pbar_update_interv": 2, "paramet": [2, 3, 5, 7, 8, 9, 10, 14, 18, 20, 35, 36, 42, 43, 45, 46, 48, 49, 51, 54, 56, 57], "int": [2, 9, 10, 18, 43, 45, 56, 57], "float": [2, 5, 8, 9, 18, 36, 45, 46, 48, 49, 54, 56, 57], "time": [2, 7, 18, 19, 36, 42, 44, 48, 49], "second": [2, 7, 9, 10, 13, 18, 19], "neg": [2, 14, 20, 56, 57], "number": [2, 5, 7, 8, 9, 10, 12, 14, 18, 27, 35, 42, 43, 56, 57], "reach": [2, 5, 18, 20, 42], "both": [2, 9, 10, 18, 19, 56, 57], "ar": [2, 5, 7, 8, 9, 10, 13, 14, 15, 18, 19, 20, 21, 25, 27, 31, 35, 36, 42, 43, 46, 47, 48, 49, 52, 56, 57], "over": [2, 7, 8, 15, 16, 17, 20, 31, 43, 56], "bool": [2, 5, 7, 9, 10, 18, 42, 45, 56], "print": [2, 9, 10, 14, 18, 20], "progress": [2, 14], "bar": [2, 14, 35], "after": [2, 5, 14, 18, 20, 36, 44, 45, 46, 53], "you": [2, 5, 7, 9, 10, 13, 14, 17, 18, 19, 20, 24, 25, 31, 42, 56, 57], "even": [2, 21], "your": [2, 14, 19, 24], "stop": 2, "criteria": 2, "ran": 2, "last": [2, 37, 44], "assum": [2, 3, 5, 8, 9, 14, 18, 25, 31, 33, 34, 35, 36, 43, 46, 47, 48, 49, 54, 56, 57], "ha": [2, 5, 8, 13, 18, 19, 23, 27, 42, 47, 48, 49, 55], "been": [2, 20, 21], "take": [2, 5, 8, 14, 17, 18, 19, 20, 38, 48, 49, 52], "receiv": [2, 5, 19, 20, 36, 48, 49, 56, 57], "choos": [2, 17, 20], "uniformli": [2, 20], "child": 2, "implement": [2, 3, 5, 8, 9, 14, 16, 17, 20, 21, 22, 23, 24, 27, 31, 36, 37, 42, 46, 48, 49, 52, 54, 56, 57], "origin": [2, 17, 19, 20, 24, 31, 33, 34, 35, 36, 37, 44, 46, 48, 49, 50], "larg": [2, 5, 20, 52, 53, 54], "http": [2, 3, 18, 24, 25], "nip": 2, "cc": 2, "4031": 2, "One": [2, 20, 43], "thing": 2, "happen": [2, 42, 46], "new": [2, 5, 7, 8, 14, 24, 45, 53], "store": [2, 5, 9, 18, 20], "level": [2, 19], "execut": [2, 5, 9, 10, 18, 20, 45, 47], "next": [2, 5, 9, 20, 35, 36, 46, 48, 49, 54, 56, 57], "These": 2, "reinvigor": [2, 7, 25], "enough": [2, 21, 36, 57], "separ": [2, 13, 19], "complet": [2, 9, 18, 31], "node": [2, 9, 10, 12, 14, 18], "longer": 2, "keep": [2, 7, 9, 36, 57], "track": [2, 7], "reinvogr": 2, "onc": [2, 5, 20, 56], "have": [2, 3, 5, 7, 8, 9, 10, 14, 15, 18, 19, 20, 21, 27, 42, 43, 45, 48, 49, 56, 57], "previous": [2, 14, 19], "version": [2, 18, 25], "basicpomcp": 2, "jl": [2, 18, 27], "github": [2, 13, 14, 18, 24, 25], "com": [2, 18, 25], "juliapomdp": [2, 31], "two": [2, 8, 9, 13, 16, 18, 20, 27, 56, 57], "equival": [2, 9, 20], "gener": [2, 5, 8, 13, 15, 17, 18, 19, 20, 21, 24, 42, 56, 57], "doesn": [2, 27, 43, 56, 57], "hurt": [2, 20, 56, 57], "featur": [2, 9, 10, 24, 27], "state_transform_func": [2, 7], "artifici": [2, 20, 24], "transform": 2, "signatur": [2, 14], "s_transform": 2, "maintain": [2, 5, 7, 18, 36], "iter": [2, 7, 14, 18, 20, 25, 27, 48, 49, 50, 56], "explain": [2, 13], "4": [2, 3, 9, 10, 18, 20, 25, 44], "stochast": [2, 20, 24, 37, 56], "No": [2, 18], "prune": [2, 18], "explod": 2, "veri": [2, 5, 20], "fast": 2, "feasibl": [2, 5, 9, 36, 48, 49, 54, 56, 57], "small": [2, 14, 20, 36, 46, 50, 51, 53, 54, 56, 57], "explicitli": [2, 7, 15, 17, 18, 20, 22, 48, 49], "horizon": [2, 14, 18, 20], "inf": [2, 18], "epsilon": [2, 8, 9, 35, 42, 43, 46], "1e": [2, 8, 9, 20, 35, 46], "lqr": [2, 3], "maximum": [2, 3, 14, 18, 31, 33, 34, 35, 42, 43, 56, 57], "likelihood": [2, 3, 8, 31, 33, 34, 35], "func_sysd": [2, 3], "func_ob": [2, 3], "jac_sysd": [2, 3], "jac_ob": [2, 3], "jac_sysd_u": [2, 3], "noise_ob": [2, 3], "noise_sysd": [2, 3], "qlarg": [2, 3], "q": [2, 3, 9, 10, 14], "planning_horizon": [2, 3], "15": [2, 3, 9, 10, 18, 20, 56], "sourc": [2, 3, 7, 9, 10, 12, 13, 18, 19, 20, 25, 31, 33, 34, 35, 36, 38, 39, 42, 43, 44, 45, 46, 47, 48, 50, 51, 52, 53, 54, 55, 56], "ut": [2, 3, 35], "ekf": [2, 3], "equat": [2, 3, 7], "12": [2, 3, 9, 18, 25, 45, 53], "13": [2, 3, 14], "f": [2, 3, 9, 35], "point": [2, 3, 18, 47, 50, 52, 54], "mt": [2, 3, 35], "cov_t": [2, 3], "np": [2, 3], "arrai": [2, 3, 8, 9, 35], "shape": [2, 3, 9, 19, 44, 46, 47], "cost": [2, 3, 7, 43, 48, 49], "need": [2, 3, 7, 17, 18, 20, 25, 31, 43, 46, 56, 57], "turn": [2, 3], "long": [2, 3], "vector": [2, 3, 8, 9, 18, 33, 35], "consist": [2, 3, 36, 57], "column": [2, 3], "stich": [2, 3], "togeth": [2, 3], "control": [2, 3, 20, 33, 45, 46, 53], "noise_t": [2, 3], "nois": [2, 3, 9, 20, 35, 48, 49, 56, 57], "possibli": [2, 3], "matrix": [2, 3], "wt": [2, 3], "term": [2, 3], "e": [2, 3, 5, 9, 10, 14, 19, 20, 21, 25, 35, 36, 42, 44, 45, 46, 47, 48, 49, 54, 56, 57], "ad": [2, 3, 5, 14], "system": [2, 3, 18, 20, 27, 33, 35], "dynam": [2, 3, 35, 46, 47], "v": [2, 3, 9, 10, 14, 18], "eq": [2, 3], "sam": [2, 3], "dimension": [2, 3, 36], "noise_obs_cov": [2, 3], "correspond": [2, 3, 17, 18, 45], "b_i": [2, 3], "u_i": [2, 3], "num_seg": [2, 3], "18": [2, 3, 9, 10, 18], "phi": [2, 3], "sum": [2, 3], "b_": [2, 3, 7, 20], "b_t": [2, 3, 20], "seg": [2, 3], "essenti": [2, 3, 15], "bu_traj": [2, 3], "b_de": [2, 3], "u_d": [2, 3], "17": [2, 3], "desir": [2, 3, 13], "covt": [2, 3], "comput": [2, 3, 7, 14, 18, 43], "list": [2, 3, 8, 9, 10, 14, 18], "begin": [2, 3, 9, 20], "segment": [2, 3], "avail": [2, 3, 5, 14, 24], "pass": [2, 3, 5, 18, 20, 36], "empti": [2, 3, 51], "b_0": [2, 3], "u_init": [2, 3], "control_bound": [2, 3], "opt_opt": [2, 3], "opt_callback": [2, 3], "solv": [2, 3, 14, 16, 19, 22, 24, 25, 28, 36, 37, 42, 50, 56], "sqp": [2, 3], "direct": [2, 3, 23], "transcript": [2, 3], "produc": [2, 3], "doc": [2, 3, 14], "scipi": [2, 3], "org": [2, 3, 14, 18, 24, 25], "tutori": [2, 3, 14, 17], "optim": [2, 3, 20], "html": [2, 3, 13, 18, 25], "opt_r": [2, 3], "lesli": [2, 20, 24], "pack": [2, 20, 24], "kaelbl": [2, 20, 24], "michael": [2, 19, 20, 24], "littman": [2, 20, 24], "anthoni": [2, 18, 20, 22, 24], "cassandra": [2, 18, 20, 22, 24], "intellig": [2, 20, 24], "101": [2, 20, 24], "99": [2, 18, 20, 24, 42, 50], "134": [2, 20, 24], "1998": [2, 20, 24], "joel": [2, 20], "veness": [2, 20], "advanc": [2, 20, 27], "neural": [2, 20], "process": [2, 20, 35, 56, 57], "2164": [2, 20], "2172": [2, 20], "2010": [2, 20], "levent": 2, "kocsi": 2, "csaba": 2, "szepesv": 2, "\u00e1": 2, "ri": 2, "bandit": 2, "european": 2, "confer": [2, 19, 20, 24], "machin": [2, 18], "learn": [2, 5, 15, 20, 21, 23, 24, 27], "282": 2, "293": 2, "springer": 2, "2006": 2, "platt": 2, "tedrak": 2, "lozano": 2, "perez": 2, "proceed": [2, 20], "robot": [2, 19, 20, 24, 27, 31, 33, 35, 38, 42, 43, 44, 45, 46, 47, 48, 49, 52, 54], "scienc": 2, "zaragoza": 2, "spain": 2, "june": 2, "doi": 2, "10": [2, 9, 10, 14, 18, 20, 24, 42, 45, 48, 49, 50, 51, 53, 54, 56, 57], "15607": 2, "rss": 2, "vi": [2, 20], "037": 2, "h": [2, 20], "lim": 2, "clair": 2, "j": 2, "tomlin": 2, "zachari": 2, "sunberg": 2, "search": [2, 9, 10, 12, 14, 20, 24, 25, 28, 29, 36, 37, 43, 44, 46, 48, 49], "guarante": 2, "continu": [2, 14, 20, 31, 33, 35], "arxiv": [2, 24], "preprint": 2, "1910": 2, "04332": 2, "2019": [2, 19, 20, 42, 44, 46], "kearn": 2, "yishai": 2, "mansour": 2, "andrew": 2, "y": [2, 43, 44, 45, 46, 48, 49, 51, 52, 53], "ng": 2, "markov": [2, 20, 56, 57], "decis": [2, 20, 56, 57], "49": [2, 9], "193": 2, "208": 2, "2002": 2, "ant": 2, "\u00f3": 2, "nio": 2, "gusmao": 2, "tapani": 2, "raiko": 2, "toward": 2, "beyond": [2, 24], "game": 2, "go": [2, 13, 16, 25, 37], "ecai": 2, "384": 2, "389": 2, "2012": 2, "import": [5, 9, 10, 15, 17, 18, 20, 25], "must": [5, 18, 20, 31, 36, 37], "hashabl": [5, 9], "oper": 5, "its": [5, 14, 15, 18, 20, 22, 23, 27, 31, 36, 37, 38, 45, 46, 47, 48, 49, 56, 57], "job": [5, 15, 20], "taken": [5, 8, 42], "care": [5, 43], "suppli": [5, 17], "OR": 5, "policy_model": [5, 9, 10, 19, 20, 42, 50], "attr_nam": 5, "attr_valu": 5, "allow": [5, 14, 19, 20, 24], "sometim": [5, 20], "model": [5, 9, 14, 18, 19, 22, 23, 24, 28, 31, 33, 36, 42, 43, 44, 48, 49, 50, 56, 57], "transit": [5, 7, 9, 18, 19, 20, 35, 36, 45, 46, 48, 49, 54, 56, 57], "current": [5, 7, 9, 10, 18, 22, 37, 45, 48, 49], "which": [5, 7, 8, 9, 10, 14, 17, 18, 20, 27, 35, 38, 45, 56, 57], "most": [5, 8, 9, 35, 36, 43, 46, 48, 49, 54, 57], "like": [5, 8, 9, 10, 13, 14, 15, 19, 20, 25, 35, 36, 43, 46, 48, 49, 54, 57], "map": [5, 8, 9, 18, 40, 43, 44, 45, 46, 47, 51], "variabl": [5, 8, 18, 55, 56], "pr": [5, 7, 8, 9, 36, 46, 48, 49, 54, 56, 57], "x": [5, 8, 9, 25, 31, 33, 35, 36, 43, 44, 45, 46, 48, 49, 51, 52, 53], "varval": 5, "evaul": 5, "world": [5, 20, 25, 36, 42, 44, 45, 46, 56], "2d": [5, 14, 42, 44, 46, 47], "gridworld": [5, 19, 43, 44, 46], "render": 5, "pygam": [5, 25, 45, 53], "Or": [5, 8, 20, 25], "could": [5, 8, 16, 17, 20, 24, 25, 27, 42, 44, 45, 46, 56], "3d": 5, "opengl": 5, "therefor": [5, 7, 36], "mind": 5, "how": [5, 16, 19, 24, 56], "so": [5, 9, 10, 13, 14, 20, 25, 27, 35, 37], "passiv": 5, "never": [5, 54], "nor": [5, 20, 56, 57], "init_st": [5, 9, 18, 34, 36, 39, 45, 48, 49, 53], "next_stat": [5, 9, 20, 35, 36, 44, 45, 46, 48, 49, 54, 56, 57], "appli": [5, 14], "assign": [5, 8], "underli": [5, 8, 35, 57], "accord": [5, 9, 19, 20, 35, 36, 46, 47, 48, 49, 52, 54, 56, 57], "type": [5, 7, 8, 9, 14, 17, 18, 35, 36, 43, 45, 46, 48, 49, 54, 56, 57], "synonym": 5, "result": [5, 7, 20, 44, 45, 46], "trigger": [5, 45], "becom": [5, 20, 45], "discount": [5, 18, 25, 36, 48, 49], "until": [5, 18], "condit": [5, 20], "reward": [5, 9, 18, 19, 20, 25, 36, 45, 46, 48, 49, 54, 56, 57], "addition": [5, 25], "exhibit": 5, "properti": [5, 9, 10, 14, 34, 44, 45, 47, 48, 49, 53], "That": [5, 18], "support": [5, 8, 15, 17, 23, 24, 27, 46], "dictionari": [5, 8, 9, 20, 43], "randomli": [5, 8, 9, 19, 35, 36, 46, 48, 49, 54, 56, 57], "tempor": 5, "abstract": [5, 8], "defin": [5, 8, 9, 14, 16, 17, 18, 19, 22, 23, 33, 34, 35, 36, 37, 38, 42, 44, 46], "semi": 5, "reinforc": [5, 23, 27], "satisfi": 5, "conveni": [5, 9, 14], "overriden": 5, "feel": [5, 27], "write": [5, 18], "boolean": 5, "whether": [5, 15, 18, 36], "technic": 5, "instanc": [5, 18, 19, 45, 48, 49, 56, 57], "env": [5, 18, 19, 20, 28, 31, 42, 50], "name": [5, 9, 18, 20, 36, 44, 48, 56, 57], "treat": [5, 20, 43, 56], "h_t": [5, 20], "reason": 5, "accommod": 5, "vari": [5, 31, 44, 46], "probabilti": 5, "arg": [5, 9, 10, 14, 20, 36, 48, 49, 54, 56, 57], "pair": 5, "mathbb": [5, 33], "denot": 5, "sim": [5, 20], "black": [5, 9], "box": 5, "creat": [5, 9, 10, 13, 18, 19, 20, 31, 56], "n_step": 5, "compon": [5, 18, 19, 20, 40, 50, 54], "oo": [5, 14, 19, 23, 44, 53], "As": [5, 17, 19], "main": [5, 18, 20, 28, 36, 48, 49, 50, 56, 57], "benefit": 5, "reduc": [5, 7, 44], "scale": 5, "exponenti": 5, "linear": [5, 35], "increas": 5, "see": [5, 8, 14, 15, 18, 19, 20, 21, 22, 24, 25, 50], "alwai": [5, 21, 37], "objid": [5, 42, 43, 44, 45, 46], "alia": [5, 9, 10], "return_oost": [5, 14, 43], "z": [5, 7, 45, 53], "mapsto": 5, "z_1": 5, "cdot": [5, 18, 35], "z_n": 5, "id": [5, 43, 44, 45, 46], "dict": [5, 7, 8, 14, 43, 44, 45, 51], "object_observ": [5, 44], "singl": [5, 9, 10, 19, 44], "prod_i": 5, "z_i": 5, "param": [5, 44], "again": 5, "chang": [5, 8, 14, 15, 20, 25, 35, 44, 46], "directli": [5, 7, 20, 22, 36, 57], "object_st": [5, 44, 46], "becaus": [5, 13, 15, 18, 20, 36, 37, 43], "caus": 5, "hashcod": 5, "incorrect": [5, 9], "kei": [5, 9, 10], "attr": 5, "request": [5, 31], "frozenset": 5, "identifi": 5, "sinc": [5, 7, 20], "hash": [5, 9, 14], "s_i": [5, 44], "made": [5, 7, 25], "str": [5, 8, 18, 45, 56], "onlin": [5, 20, 31, 50], "pure": 5, "underneath": 5, "hood": 5, "Its": 5, "output": [5, 13, 18, 25], "expect": [5, 18, 25], "same": [5, 7, 8, 14, 18, 20, 52, 54, 56], "current_histogram": 7, "state_mapp": [7, 8], "oarg": 7, "targ": 7, "normal": [7, 8, 36, 46, 48, 49, 57], "static_transit": 7, "next_state_spac": 7, "determinist": [7, 9, 20, 35, 46, 47, 48, 49, 54], "sum_": 7, "addit": [7, 18, 21, 24], "indic": [7, 35, 45], "thu": [7, 19, 44], "help": [7, 9, 10, 18, 19, 24], "avoid": [7, 14, 15, 47], "nest": 7, "alreadi": [7, 23], "prohibit": 7, "consid": [7, 19, 42, 45], "effici": 7, "contain": [7, 9, 10, 13, 14, 18, 20, 22, 27, 47, 56, 57], "part": [7, 18], "know": [7, 37, 42], "num_particl": [7, 8, 36, 42, 43, 48, 49, 50, 51], "simpli": [7, 20], "At": [7, 35], "least": 7, "more": [7, 9, 10, 13, 16, 17, 18, 19, 20, 21, 23, 24, 25, 27, 56, 57], "ok": 7, "current_particl": 7, "either": [7, 14, 18, 19, 20, 56, 57], "todo": [7, 14], "test": [7, 9, 14, 18, 28, 29], "prob": 8, "09": [8, 35, 46], "unweight": 8, "inherit": [8, 14, 20], "1000": [8, 42, 46, 50], "approxim": [8, 27, 52, 54], "feed": 8, "through": [8, 9, 10, 17, 20, 36, 42], "multipl": [8, 23], "interpret": [8, 19, 42, 44, 45], "those": [8, 20, 25], "approx_method": 8, "distance_func": 8, "drawn": 8, "nearest": 8, "queri": 8, "match": [8, 14], "closest": 8, "exact": [8, 14, 20, 36], "uniqu": 8, "aggreg": 8, "numer": [8, 18, 27], "densiti": 8, "multivari": 8, "Not": [8, 37], "isn": 8, "arbitrarili": 8, "deal": [9, 34], "percent": 9, "rgb": 9, "255": [9, 45, 53], "hx": 9, "string": [9, 10, 18, 42, 45, 57], "len": [9, 17], "ctype": 9, "cython": [9, 14, 24, 25, 27, 28, 29], "dct": 9, "make": [9, 10, 13, 14, 15, 19, 24, 25, 27, 37, 43], "easier": [9, 10, 14], "core": [9, 10, 15], "incorpor": [9, 10], "design": [9, 10, 24], "eas": [9, 10], "pdb": [9, 10, 56], "ipdb": [9, 10], "session": [9, 10], "minim": [9, 10], "usag": [9, 10], "pomdp_problem": [9, 10, 14, 18, 19, 21, 24, 25], "tiger": [9, 10, 14, 17, 18, 19, 24, 25, 28, 29], "tigerproblem": [9, 10, 18, 20, 28, 56, 57], "suppos": [9, 10], "too": [9, 10], "95": [9, 10, 18, 20, 36, 48, 49], "4096": [9, 10], "200": [9, 10], "tiger_problem": [9, 10, 14, 18, 20, 28, 29], "dd": [9, 10, 56], "set_trac": [9, 10], "program": [9, 10, 18, 22], "enter": [9, 10], "debugg": [9, 10, 12], "_vnodepp": [9, 10], "4095": [9, 10], "19": [9, 10, 18], "529": [9, 10], "\u2080listen": [9, 10], "_qnodepp": [9, 10], "4059": [9, 10], "\u2080tiger": [9, 10], "2013": [9, 10], "16": [9, 10], "586": [9, 10], "1883": [9, 10], "1441": [9, 10], "8": [9, 10, 18, 25, 36, 54], "300": [9, 10], "out": [9, 10, 18, 19, 27], "entir": [9, 10, 20, 56, 57], "\u2081open": [9, 10], "139": [9, 10], "847": [9, 10], "\u2082open": [9, 10], "112": [9, 10, 18], "57": [9, 10], "191": [9, 10], "text": [9, 10, 18], "retriev": [9, 10], "subtre": [9, 10], "index": [9, 10, 18, 24], "listen": [9, 10, 14, 18, 20, 25, 56, 57], "2044": [9, 10], "160": [9, 10], "open": [9, 10, 18, 20, 56, 57], "148": [9, 10], "634": [9, 10], "20": [9, 10, 14, 18, 48], "237": [9, 10], "500": [9, 10, 42, 50], "obtain": [9, 10], "sequenc": [9, 10, 14, 20], "\u2081tiger": [9, 10], "1955": [9, 10], "947": [9, 10], "768": [9, 10], "022": [9, 10], "462": [9, 10], "395": [9, 10], "000": [9, 10], "247": [9, 10], "stand": [9, 10, 20, 24, 56, 57], "best": [9, 10, 14], "brows": [9, 10], "method": [9, 10, 14], "document": [9, 10, 14, 16, 18, 27], "futur": [9, 10], "organ": [9, 10, 19, 20], "kind": [9, 10], "total": [9, 10, 18], "start": [9, 10, 20, 25, 36, 37, 45], "largest": [9, 10], "edg": [9, 10, 18], "equal": [9, 10, 20, 48, 49, 56, 57], "as_debugg": [9, 10], "Will": [9, 10], "high": [9, 10, 19, 27], "huge": [9, 10], "interact": [9, 10, 15], "along": [9, 10], "move": [9, 10, 19, 25, 31, 36, 37, 48, 49, 54, 55], "parent": [9, 10, 45], "first": [9, 10, 13, 18, 19, 20, 25, 33, 35, 48, 49], "preset": [9, 10], "seq": [9, 10], "understand": [9, 10, 15], "_nodepp": [9, 10], "dest": [9, 10], "Such": [9, 10], "except": [9, 10, 45, 53], "static": [9, 10, 45, 46, 48, 49, 53, 56], "parent_edg": [9, 10], "indent": [9, 10], "include_children": [9, 10], "df": [9, 10], "gether": [9, 10], "statist": [9, 10], "about": [9, 10, 14, 19, 36, 43, 47, 48, 49], "colorstr": [9, 10], "assort": 9, "p1": [9, 47, 48, 49], "p2": [9, 47, 48, 49], "vec1": 9, "vec2": 9, "scalar": 9, "th": [9, 45, 47, 53], "dx": 9, "dy": 9, "dz": 9, "v1": 9, "v2": 9, "06": [9, 18], "python": [9, 14, 18, 19, 20, 24, 25, 27, 36, 50], "oldvalu": 9, "oldmin": 9, "oldmax": 9, "newmin": 9, "newmax": 9, "obj": 9, "arr": 9, "end": [9, 45], "48": 9, "8320": 9, "8321": 9, "50": [9, 18], "8322": 9, "51": [9, 18], "8323": 9, "52": [9, 18], "8324": 9, "53": 9, "8325": 9, "54": 9, "8326": 9, "55": 9, "8327": 9, "56": 9, "8328": 9, "8329": 9, "utilti": 9, "xval": 9, "yval": 9, "size": [9, 14, 18, 45, 47, 53], "label": 9, "connect": [9, 27, 42], "style": 9, "linewidth": 9, "xlabel": 9, "ylabel": 9, "loc": 9, "lower": [9, 45], "bbox_inch": 9, "tight": 9, "vert": 9, "ax": [9, 12], "edgecolor": 9, "verts0": 9, "verts1": 9, "verts_i": 9, "xy": [9, 44, 55], "vertic": 9, "numpi": [9, 35], "color0": 9, "color1": 9, "color_i": 9, "hex": 9, "charact": [9, 45], "xxxxxx": 9, "polygoncollect": 9, "axi": 9, "zorder": 9, "alpha": [9, 18], "linestyl": 9, "center": [9, 47], "radiu": [9, 45, 47], "fill": 9, "label_text": 9, "text_color": 9, "some": [9, 14, 16, 18, 20, 21, 25, 27, 42], "particular": 9, "data": 9, "piec": 9, "correct": [9, 15, 20], "typic": [9, 20], "tabular": [9, 14], "built": [9, 13, 14, 15], "specifi": [9, 13, 14, 17, 18, 20, 56, 57], "nextstat": 9, "emit": 9, "pattern": 9, "quickli": [9, 16, 24], "build": [9, 14, 15, 18, 19, 24, 25], "typographi": 9, "purpos": [9, 19, 24], "displai": [9, 12, 25], "them": [9, 16, 20, 25, 27, 43], "x1b": 9, "97m": 9, "96m": 9, "95m": 9, "94m": 9, "92m": 9, "93m": 9, "91m": 9, "1m": 9, "0m": 9, "shown": [9, 19, 35], "visualize_pouct_search_tre": 12, "visit_threshold": 12, "anonym": 12, "anonymize_act": 12, "anonymize_observ": 12, "output_fil": 12, "use_dot": 12, "visit": [12, 14, 17], "caveat": 12, "well": [12, 19, 20, 46, 56, 57], "shallow": 12, "larger": 12, "pleas": [12, 24], "custom": [12, 19], "herit": 12, "a1": 12, "a2": 12, "o1": 12, "o2": 12, "sphinx": [13, 14], "web": 13, "page": [13, 24, 25], "There": [13, 18, 20, 21, 25, 27, 31, 54], "Their": 13, "directori": [13, 25], "cd": 13, "py": [13, 14, 19, 20], "_sphinx_src": 13, "apidoc": 13, "api": 13, "rst": 13, "file": [13, 14, 19, 20, 25, 27, 42], "argument": [13, 14, 17], "re": [13, 20, 34, 45, 53, 56], "readm": 13, "read": [13, 20], "me": 13, "Then": [13, 20, 42], "includ": [13, 14, 15, 42, 43, 50], "top": [13, 14], "repositori": [13, 25], "websit": [13, 14, 25], "construct": [13, 18, 20, 42], "symbol": 13, "link": [13, 14, 18, 19, 24], "ln": 13, "cannot": [13, 36, 37], "access": [13, 20, 24], "remov": [13, 14, 18], "site": 13, "deploi": 13, "fundament": 15, "block": [15, 19, 36], "formal": 15, "encapsul": 15, "few": 15, "pomdp_pi": [14, 15, 16, 17, 19, 20, 21, 22, 23, 25, 27, 36, 50], "around": [15, 27], "convei": 15, "idea": [15, 20], "abov": [15, 18, 19, 20, 22, 25], "gist": [14, 15], "captur": 15, "versu": 15, "much": [14, 15], "sens": [15, 19, 45], "hold": [15, 51], "instead": [14, 15, 20, 42, 44, 46, 56, 57], "own": [14, 15, 46], "verifi": [14, 15, 25], "valid": [15, 46, 47], "diagram": 15, "langl": 15, "omega": [15, 18, 22, 33, 35], "rangl": 15, "discuss": 16, "simpler": [14, 16, 27, 42], "complic": [16, 19, 20, 24, 56, 57], "interest": 16, "former": 16, "latter": 16, "structur": [16, 19, 24], "project": [16, 19, 23, 24, 27], "convent": [16, 24, 47], "below": [17, 19, 21, 25], "minimum": 17, "def": [17, 20], "rais": [17, 20], "notimplementederror": 17, "els": [17, 18, 20, 44, 46], "notion": 17, "narrow": 17, "express": 17, "detail": [17, 18, 19, 20, 22, 56], "paragraph": 17, "count": [17, 25, 45], "account": 17, "nu": [18, 22], "hope": [18, 21], "u": [18, 33, 35, 36], "mani": [18, 27], "librari": [14, 18, 22, 24, 25], "input": [18, 22, 44, 45], "written": [18, 20, 24, 27], "format": [14, 18, 20, 27], "pomdpx": [14, 18, 27], "pomdpconvert": 18, "toolkit": 18, "to_pomdp_fil": [14, 18], "to_pomdpx_fil": 18, "convers": [14, 18], "output_path": 18, "float_precis": [14, 18], "www": [18, 25], "spec": [18, 20, 56], "independ": 18, "blank": 18, "decim": 18, "order": [18, 20, 31, 33], "pomdpconvert_path": 18, "check": [18, 19, 20, 27, 48, 49], "adacompnu": 18, "instruct": [18, 25], "download": [18, 25], "ubuntu": 18, "04": 18, "gcc": 18, "bigbird": 18, "comp": 18, "edu": 18, "sg": 18, "pmwiki": 18, "farm": 18, "appl": [18, 27], "php": 18, "pomdpxdocument": 18, "binari": [18, 22], "let": [18, 20], "tigerst": [18, 28, 56, 57], "filenam": [18, 19], "test_tig": 18, "softwar": [18, 25, 27], "src": 18, "vi_prun": 18, "pomdp_solve_path": 18, "pomdp_nam": 18, "temp": 18, "remove_generated_fil": 18, "return_policy_graph": 18, "definit": [18, 20], "pomdp_solv": [14, 18], "compil": 18, "command": [18, 19, 25], "stop_criteria": 18, "weak": 18, "time_limit": 18, "pg": 18, "instal": [14, 18, 24], "appear": [18, 27, 31], "recommend": [18, 19, 25], "100": [18, 20, 36, 42, 43, 51, 56, 57], "rang": [18, 19, 20, 46, 47], "isinst": [18, 20], "cur_belief": [18, 20], "graph": [18, 19, 42, 44, 46], "new_belief": [18, 20], "pid": 18, "8239": 18, "mcgs_prune_freq": 18, "verbos": 18, "context": 18, "done": [18, 20, 27, 42], "epoch": 18, "00": 18, "sec": 18, "err": 18, "39": 18, "96": 18, "97": 18, "98": 18, "01": [18, 42, 43, 46], "40": 18, "solut": 18, "found": [18, 19, 25, 52], "user": [18, 20], "hr": 18, "min": 18, "lp_solv": 18, "report": 18, "lp": 18, "instabl": 18, "85": 18, "9697986575573173": 18, "03020134244268276": 18, "pomdpsol_path": 18, "timeout": 18, "30": [18, 45, 53], "memori": 18, "precis": [18, 31, 33], "logfil": 18, "anytim": [18, 50, 52, 54], "pomdpsol": 18, "limit": 18, "mb": 18, "regret": 18, "less": 18, "than": [18, 27], "finish": 18, "log": [14, 18], "stdout": 18, "stderr": 18, "_": 18, "000001": 18, "load": [14, 18, 24, 28, 29], "trial": [18, 28, 50], "backup": 18, "lbound": 18, "ubound": 18, "92": 18, "8205": 18, "821": 18, "2981": 18, "63": 18, "7547": 18, "70": 18, "0528": 18, "103": 18, "35722": 18, "3746": 18, "0174": 18, "155": 18, "44093": 18, "45": 18, "1431": 18, "38": [18, 28, 29], "7021": 18, "205": 18, "1184": 18, "36": 18, "4409": 18, "24": 18, "3225": 18, "1255": 18, "3714": 18, "13808e": 18, "21": 18, "41": 18, "1300": 18, "76277e": 18, "42": 18, "1350": 18, "75044e": 18, "43": 18, "1393": 18, "22729e": 18, "07": 18, "11": [18, 25], "target": [18, 19, 20, 42, 43, 45, 52, 54, 56], "extend": [14, 18, 19, 20, 21], "encod": 18, "alpha_path": 18, "pg_path": 18, "parse_pomdp_solve_output": 18, "pointer": 18, "incom": 18, "offlin": 18, "collect": 18, "associ": 18, "dot": 18, "product": 18, "lead": [18, 19], "domin": 18, "activ": [18, 27], "finit": [18, 20, 36, 37, 56], "max_": 18, "gamma": 18, "policy_path": 18, "parse_appl_policy_fil": 18, "involv": 19, "whose": 19, "better": 19, "mainten": 19, "readabl": 19, "task": [19, 23, 24, 27, 28, 29, 36], "rel": 19, "share": [19, 24], "wandzel": 19, "et": 19, "al": 19, "slightli": 19, "room": [19, 42], "topolog": [19, 42, 44, 46], "formul": 19, "orient": [19, 23, 37, 38, 42, 43, 44, 46, 47], "our": [19, 20, 27, 31, 47], "w": [19, 35, 44], "grid": [19, 36, 44, 46, 47, 48, 49, 54], "cell": [19, 52, 54], "three": [19, 20], "categori": 19, "motion": [19, 38, 42, 44, 46, 48, 49, 52], "look": [19, 25, 38, 44, 46], "region": [19, 45, 47], "find": [14, 19, 24, 25, 44, 46], "within": [19, 46, 47], "fan": [19, 44, 46, 47], "adjust": 19, "angl": [19, 45, 47], "laser": [19, 45, 47, 50], "scanner": [19, 45, 47], "360": [19, 47], "degre": [19, 45, 47], "sensor": [19, 20, 42, 43, 44, 45, 46, 48, 49], "disk": 19, "occlus": [19, 45, 47], "scan": [19, 45, 47], "beam": [19, 45, 47], "artifact": 19, "due": [14, 19, 47], "discret": [19, 31, 33], "figur": [19, 31, 35, 36], "screenshot": 19, "frame": 19, "imag": [14, 19], "circl": [19, 25], "perfect": [19, 46, 48, 49], "third": 19, "show": [14, 19, 24], "later": 19, "summari": 19, "procedur": [19, 20], "instanti": [19, 42], "good": [19, 25, 48, 49], "squeez": 19, "everyth": 19, "giant": 19, "might": [19, 20, 47, 56, 57], "reus": 19, "free": [19, 20, 23, 24, 27, 48, 49, 56, 57], "whatev": 19, "save": 19, "grid_map": [19, 42, 43, 46, 50, 51, 53, 54], "example_world": [19, 28, 29], "evid": 19, "role": 19, "mosoopomdp": [19, 28, 42], "logic": 19, "feedback": [19, 20, 56, 57], "loop": [19, 20, 56, 57], "m": [14, 19, 24, 25, 36, 50], "multi_object_search": [19, 25, 28, 29], "place": [19, 20, 36, 54], "obstacl": [19, 43, 45, 47], "pose": [19, 42, 44, 46, 47], "equip": [19, 46], "yet": [14, 19, 31, 37], "equip_sensor": [19, 42, 45], "make_laser_sensor": [19, 42, 45], "make_proximity_sensor": [19, 42, 45], "arthur": 19, "yoonseon": 19, "oh": 19, "fishman": 19, "nishanth": 19, "kumar": 19, "stefani": [19, 20, 24], "tellex": [19, 20, 24], "intern": [19, 20], "autom": [19, 20], "icra": [19, 42, 44, 46], "7194": 19, "7200": 19, "ieee": 19, "classic": [20, 48, 56, 57], "descript": [20, 31, 36, 37, 42, 44, 45, 46, 48, 49, 50, 56, 57], "introduct": [20, 56, 57], "kamalzadeh": [20, 56, 57], "hahsler": [20, 56, 57], "put": [20, 56, 57], "behind": [20, 56, 57], "door": [20, 56, 57], "treasur": [20, 56, 57], "front": [20, 47, 56, 57], "close": [20, 56, 57], "decid": [20, 56, 57], "get": [20, 25, 46, 50, 56, 57], "posit": [20, 31, 33, 34, 35, 37, 38, 48, 49, 54, 55, 56, 57], "awai": [20, 31, 54, 56, 57], "wait": [20, 56, 57], "neither": [20, 56, 57], "accur": [20, 56, 57], "hear": [20, 56, 57], "actual": [20, 31, 37, 42, 47, 56, 57], "vice": [20, 56, 57], "versa": [20, 56, 57], "encourag": 20, "valueerror": 20, "invalid": [20, 47], "__hash__": 20, "__eq__": 20, "side": [20, 36, 37], "boil": 20, "heard": 20, "growl": 20, "thresh": 20, "uniform": [20, 43, 48, 49, 50, 51, 56], "similarli": 20, "reset": [20, 56], "otherwis": [20, 36, 56], "stai": [14, 20, 54, 56], "startswith": 20, "choic": 20, "easili": 20, "tabl": 20, "flexibl": 20, "intract": 20, "determin": [20, 33, 47, 48, 49], "sever": [20, 21], "would": [14, 20, 27], "usual": 20, "human": 20, "engin": 20, "sort": 20, "guid": 20, "sure": [20, 43], "guidanc": 20, "caution": 20, "realli": [20, 43], "sai": 20, "inject": 20, "final": 20, "straightforward": 20, "commonli": 20, "_reward_func": 20, "elif": 20, "With": [20, 54], "abl": [14, 20], "mostli": 20, "obs_nois": [20, 56], "init_true_st": [20, 56, 57], "super": 20, "notic": 20, "constructor": 20, "now": [14, 20], "standard": 20, "a_t": 20, "s_t": 20, "rightarrow": 20, "s_": 20, "r_t": 20, "o_t": 20, "h_": 20, "cup": [20, 44], "unless": 20, "repeat": 20, "110": 20, "test_plann": [20, 28, 36, 48, 49, 56, 57], "nstep": [20, 36, 48, 49, 56, 57], "ennviron": 20, "skip": [14, 20], "estim": [20, 33], "percept": 20, "stack": 20, "saniti": 20, "come": 20, "extern": [14, 20, 22, 24, 25, 36, 57], "automat": 20, "num": 20, "short": 20, "abel": 20, "elli": 20, "hershkowitz": 20, "gabriel": 20, "barth": 20, "maron": 20, "stephen": 20, "brawner": 20, "kevin": 20, "farrel": 20, "jame": 20, "macglashan": 20, "goal": [20, 31, 37], "twenti": 20, "fifth": 20, "schedul": 20, "2015": 20, "yuchen": 20, "xiao": 20, "sammi": 20, "katt": 20, "andrea": 20, "ten": 20, "pa": 20, "shengjian": 20, "chen": 20, "christoph": 20, "amato": 20, "clutter": 20, "welcom": [21, 24], "light": [14, 21, 24, 28, 29, 33, 34, 35], "dark": [14, 21, 24, 28, 29, 33, 34, 35], "maze": 21, "multi": [14, 21, 23, 24, 25, 28, 29, 43, 44, 46], "sarsop": [14, 22, 25, 27], "rl": 23, "transfer": [23, 24], "research": [23, 24, 27], "baslin": 23, "comprehens": 24, "why": 24, "clean": 24, "intuit": 24, "relat": [24, 46], "peopl": 24, "commun": [24, 25, 27], "artial": 24, "bservabl": 24, "arkov": 24, "ecis": 24, "rocess": 24, "major": 24, "languag": 24, "what": 24, "changelog": 24, "mo": [14, 24, 25, 28, 29, 44], "principl": 24, "integr": [14, 24], "cite": 24, "inproceed": 24, "zheng2020pomdp_pi": 24, "titl": 24, "_py": 24, "author": 24, "zheng": 24, "kaiyu": 24, "booktitl": 24, "icap": 24, "2020": 24, "workshop": 24, "planrob": 24, "year": 24, "url": 24, "icaps20subpag": 24, "wp": 24, "upload": 24, "14": [24, 25, 36], "planrob_2020_paper_3": 24, "pdf": 24, "2004": [24, 48, 49], "10099": 24, "rocksampl": [14, 24, 25, 28, 29], "unload": [14, 24, 28, 29], "tag": [14, 24, 28, 29], "virtualenv": 25, "pip": [14, 25], "manag": 25, "offici": 25, "maco": 25, "On": 25, "window": [14, 25], "wiki": 25, "latest": 25, "releas": [14, 25], "clone": 25, "git": 25, "h2r": 25, "setup": [14, 25], "locat": [25, 36, 37, 43, 47, 48, 49, 52, 54], "pyx": [14, 25], "pyd": 25, "rebuild": 25, "messi": 25, "someth": [25, 44, 46], "66": 25, "bad": [25, 48, 49], "cumul": 25, "__num_sims__": 25, "1217": 25, "______id______": 25, "210": 25, "_____g": 25, "b_____": 25, "hello": 25, "xyth": [25, 44], "north": [25, 42, 44, 48, 49], "mosooobserv": [25, 42, 44, 45], "542": 25, "506": 25, "test_al": 25, "via": [25, 27], "hub": 25, "credit": 25, "romain": 25, "egel": 25, "think": 27, "peer": 27, "easi": 27, "ro": 27, "acceler": 27, "pomdpi": 27, "suffici": 27, "convolut": 27, "potenti": [14, 27], "clearer": 27, "pars": 27, "art": 27, "great": 27, "julia": 27, "known": [27, 48, 49], "suit": [27, 31], "analysi": 27, "besid": 27, "librai": 27, "port": 27, "ai": 27, "toolbox": 27, "bind": 27, "focus": 27, "lear": 27, "beliefmdp": 27, "belief_upd": [28, 42, 50, 51], "unittest": [28, 42, 45, 46, 50, 53], "random_world": [28, 42], "rocksample_problem": [28, 29], "rocktyp": [28, 48, 49], "moveact": [28, 48, 49], "sampleact": [28, 48, 49], "checkact": [28, 48, 49], "rstransitionmodel": [28, 48, 49], "rsobservationmodel": [28, 48, 49], "rsrewardmodel": [28, 48, 49], "rspolicymodel": [28, 48, 49], "rocksampleproblem": [28, 48, 49], "init_particles_belief": [28, 48, 49], "tigeract": [28, 56, 57], "tigerobserv": [28, 56, 57], "light_dark": [28, 29], "problem_discret": [28, 29], "discretelightdark": [28, 31], "load_unload": [28, 29], "lustat": [28, 36], "luaction": [28, 36], "luobserv": [28, 36], "luobservationmodel": [28, 36], "lutransitionmodel": [28, 36], "lurewardmodel": [28, 36], "lupolicymodel": [28, 36], "loadunloadproblem": [28, 36], "generate_random_st": [28, 36], "generate_init_belief": [28, 36], "experi": [28, 29, 31], "tagproblem": [28, 50], "local": 31, "plane": 31, "befor": 31, "approach": 31, "abil": 31, "itself": [31, 36], "upon": 31, "quadrat": 31, "horizont": 31, "coordin": [31, 35], "configur": [31, 45], "ultim": 31, "illustr": 31, "intens": 31, "magnitud": 31, "unknown": 31, "variant": 31, "kept": 31, "pull": 31, "lightdarkdomain": 31, "repo": 31, "lightdarkenviron": [31, 34], "const": [31, 34, 35], "lightdarkviz": [31, 34], "log_posit": [31, 34], "set_goal": [31, 34], "set_initial_belief_po": [31, 34], "noise_covari": [31, 35], "func": [31, 35], "jac_dx": [31, 35], "func_nois": [31, 35], "jac_du": [31, 35], "subseteq": 33, "veloc": 33, "x_t": [33, 35], "x_rang": 34, "y_rang": 34, "goal_po": 34, "m_0": 34, "path_color": 34, "254": 34, "path_styl": 34, "path_width": 34, "ident": 35, "zero": [14, 35, 37], "omegasimmathc": 35, "rac": 35, "s_x": 35, "ext": 35, "notat": 35, "element": 35, "fig": 35, "u_t": 35, "xt": [35, 45], "jacobian": 35, "respect": 35, "var_sysd": 35, "distinguish": 36, "perceiv": [36, 37], "tell": 36, "statu": 36, "ob": 36, "extrem": [36, 57], "dumb": [36, 57], "load_unload_problem": 36, "presenc": 37, "absenc": 37, "wall": [37, 38], "squar": 37, "non": 37, "slip": 37, "attempt": [14, 37], "had": 37, "consequ": 37, "positit": 38, "mazeenviron": 39, "scheme": [42, 44], "robot_id": [42, 43, 44, 45, 46, 47], "belief_rep": [42, 43], "agent_has_map": 42, "cours": 42, "scenario": 42, "past": 42, "give": 42, "next_robot_st": [42, 46], "max_tim": [42, 50], "120": [42, 50], "max_step": [42, 50], "findact": [42, 44], "width": [42, 43, 46, 47, 50, 53, 55], "length": [42, 43, 46, 47, 50, 53, 55], "num_obj": 42, "num_obstacl": 42, "robot_char": 42, "mosenviron": [42, 45], "interpret_robot_id": [42, 45], "object_color": [42, 45], "mosviz": [42, 45, 53], "img_width": [42, 45, 50, 53], "img_height": [42, 45, 50, 53], "last_observ": [42, 45, 50, 53], "draw_robot": [42, 45, 50, 53], "draw_observ": [42, 45, 50, 53], "draw_belief": [42, 45, 50, 53], "on_init": [42, 45, 50, 53], "on_ev": [42, 45, 50, 53], "on_loop": [42, 45, 50, 53], "on_rend": [42, 45, 50, 53], "on_cleanup": [42, 45, 50, 53], "on_execut": [42, 45, 50, 53], "render_env": [42, 45, 50, 53], "motionact": [42, 44, 47], "scheme_xyth": [42, 44], "east": [42, 44, 48, 49], "west": [42, 44, 48, 49], "south": [42, 44, 48, 49], "scheme_vw": [42, 44], "forward": [42, 44], "backward": [14, 42, 44], "scheme_xi": [42, 44], "east2d": [42, 44, 55], "west2d": [42, 44, 55], "north2d": [42, 44, 55], "south2d": [42, 44, 55], "lookact": [42, 44], "objectobserv": [42, 44, 46], "null": [42, 44, 46], "for_obj": [42, 44], "robotst": [42, 44], "robot_pos": [42, 44, 47], "objects_found": [42, 44], "mosoost": [42, 44], "object_pos": [42, 44], "mosobservationmodel": [42, 46], "objectobservationmodel": [42, 46], "mosrewardmodel": [42, 46], "goalrewardmodel": [42, 46], "mostransitionmodel": [42, 46], "staticobjecttransitionmodel": [42, 46], "robottransitionmodel": [42, 46], "if_move_bi": [42, 46, 50, 54], "valid_pos": [42, 46, 50, 54, 55], "in_boundari": [42, 46], "mosag": 43, "init_robot_st": 43, "object_id": [43, 46], "dim": [43, 45, 46], "clear_histori": [43, 50, 51], "custum": [43, 51], "mosoobelief": 43, "initialize_belief": [43, 50, 51], "robot_orient": 43, "unspecifi": 43, "radian": 43, "45deg": 44, "forc": 44, "everi": [44, 48, 49], "drop": 44, "distance_cost": 44, "motion_nam": 44, "141592653589793": 44, "71238898038469": 44, "5707963267948966": 44, "vw": 44, "7853981633974483": 44, "objpos": 44, "s_1": 44, "s_2": 44, "s_n": 44, "s_r": 44, "leq": 44, "sr": 44, "objclass": 44, "camera_direct": 44, "overrid": 45, "worldstr": [45, 50, 53, 55], "rx": [45, 53], "fov": [45, 47], "90": [45, 47], "min_rang": [45, 47], "max_rang": [45, 47], "obsticl": 45, "replac": 45, "upper": 45, "letter": 45, "serv": 45, "signal": 45, "laser2dsensor": [45, 47], "robot_nam": 45, "worldmap": 45, "angle_incr": [45, 47], "dist_rang": 45, "angular": 45, "distanc": [45, 47], "measur": 45, "rad": 45, "proxim": [45, 47], "occlusion_en": [45, 47], "fp": [45, 53], "viz_observ": 45, "img": [45, 53], "ry": [45, 53], "rth": [45, 53], "target_color": [45, 53], "init": [45, 53], "event": [45, 53], "display_surf": [45, 53], "occup": [46, 51], "target_object": 46, "big": [46, 50, 51, 53, 54], "detect": 46, "necessarili": 46, "next_object_st": 46, "check_collis": 46, "robot_st": 46, "pose_objid": 46, "overlap": 46, "assist": 47, "collis": 47, "gridmap": [47, 50, 51, 54, 55], "valid_mot": [47, 50, 54, 55], "all_motion_act": 47, "bump": 47, "assumpt": 47, "to_rad": 47, "deg": 47, "in_rang": 47, "val": 47, "env_stat": 47, "within_rang": 47, "visibl": [14, 47], "gap": 47, "sensing_region_s": 47, "in_field_of_view": 47, "view_angl": 47, "field": [14, 47, 56, 57], "view": [14, 47], "180": 47, "270": 47, "shoot_beam": 47, "shoot": 47, "bear": 47, "valid_beam": 47, "dist": 47, "increment": 47, "mosobserv": 47, "proximitysensor": 47, "k": [48, 49], "uai": [48, 49], "rocktype_1": [48, 49], "rocktype_2": [48, 49], "rocktype_k": [48, 49], "rocktype_i": [48, 49], "terminalst": [48, 49], "rock": [48, 49], "check_i": [48, 49], "smartli": [48, 49], "check_1": [48, 49], "check_k": [48, 49], "four": [48, 49], "noisi": [48, 49], "eta": [48, 49], "exit": [48, 49], "area": [48, 49], "being": [48, 49], "invert": [48, 49], "rock_id": [48, 49], "qualiti": [48, 49], "rock_loc": 48, "in_exit_area": [48, 49], "half_efficiency_dist": 48, "random_free_loc": [48, 49], "not_free_loc": [48, 49], "nxn": [48, 49], "generate_inst": [48, 49], "print_stat": [48, 49], "rsaction": [48, 49], "rsobserv": [48, 49], "rsstate": [48, 49], "run_rocksampl": 48, "regular": 50, "initialize_particles_belief": [50, 51], "tagag": [50, 51], "tagact": [50, 52], "tagobserv": [50, 52], "tagstat": [50, 52], "tagenviron": [50, 53], "from_str": [50, 53, 54, 55], "tagviz": [50, 53], "free_cel": [50, 54, 55], "motion_polici": [50, 54], "tagtargetmotionpolici": [50, 54, 55], "tagobservationmodel": [50, 54], "tagpolicymodel": [50, 54], "tagrewardmodel": [50, 54], "tagtransitionmodel": [50, 54], "init_robot_posit": [50, 51], "init_target_posit": 50, "pr_stai": [50, 51, 53, 55], "belief_typ": 50, "hist": 50, "planner_typ": 50, "target_posit": [52, 55], "person": 52, "robot_posit": [52, 55], "target_found": 52, "ohterwis": 54, "anyth": 54, "stochaist": 54, "movement": 54, "closer": 54, "target_motion_polici": 54, "obstacle_pos": 55, "all_mot": 55, "next_target_posit": 55, "valid_target_motion_act": 55, "run_tig": 56, "tigerobservationmodel": [56, 57], "tigerpolicymodel": [56, 57], "tigerrewardmodel": [56, 57], "tigertransitionmodel": [56, 57], "build_act": [56, 57], "build_observ": [56, 57], "build_set": [56, 57], "build_stat": [56, 57], "fact": 56, "debug_tre": 56, "obs_prob": 57, "trans_prob": 57, "fix": 14, "cpdef": 14, "cdef": 14, "failur": 14, "29": 14, "comment": 14, "sp": 14, "minor": 14, "bug": 14, "__str__": 14, "confus": 14, "improv": 14, "clarifi": 14, "gave": 14, "cryingbabi": 14, "pygraphviz": 14, "inspect": 14, "refactor": 14, "cli": 14, "simplifi": 14, "__ne__": 14, "reorgan": 14, "break": 14, "unnecessari": 14, "compat": 14, "pickl": 14, "edit": 14, "cimport": 14, "ed": 14, "pypi": 14, "value_funct": 14, "18fc58e0": 14, "cfc88e8d8": 14, "719c2edf5": 14, "docker": 14, "issu": 14, "citat": 14, "resolv": 14, "max": 14, "among": 14, "infin": 14, "thank": 14, "jason": 14, "clarif": 14, "convert": 14, "were": 14, "calcul": 14, "divid": 14, "thrown": 14, "infinit": 14, "anoth": 14, "differenti": 14, "per": 14, "faster": 14, "readi": 14, "changeabl": 14, "rewritten": 14, "cleaner": 14, "wheel": 14, "properli": 14, "tame": 14}, "objects": {"pomdp_problems": [[30, 0, 0, "-", "lasertag"], [31, 0, 0, "-", "light_dark"], [36, 0, 0, "-", "load_unload"], [37, 0, 0, "-", "maze"], [48, 0, 0, "-", "rocksample"], [50, 0, 0, "-", "tag"]], "pomdp_problems.light_dark": [[32, 0, 0, "-", "agent"], [33, 0, 0, "-", "domain"], [34, 0, 0, "-", "env"], [35, 0, 0, "-", "models"], [31, 0, 0, "-", "problem_discrete"]], "pomdp_problems.light_dark.agent": [[32, 0, 0, "-", "belief"]], "pomdp_problems.light_dark.domain": [[33, 0, 0, "-", "action"], [33, 0, 0, "-", "observation"], [33, 0, 0, "-", "state"]], "pomdp_problems.light_dark.domain.action": [[33, 1, 1, "", "Action"]], "pomdp_problems.light_dark.domain.observation": [[33, 1, 1, "", "Observation"]], "pomdp_problems.light_dark.domain.observation.Observation": [[33, 2, 1, "", "PRECISION"], [33, 3, 1, "", "discretize"]], "pomdp_problems.light_dark.domain.state": [[33, 1, 1, "", "State"]], "pomdp_problems.light_dark.env": [[34, 0, 0, "-", "env"], [34, 0, 0, "-", "visual"]], "pomdp_problems.light_dark.env.env": [[34, 1, 1, "", "LightDarkEnvironment"]], "pomdp_problems.light_dark.env.env.LightDarkEnvironment": [[34, 4, 1, "", "const"], [34, 4, 1, "", "light"]], "pomdp_problems.light_dark.env.visual": [[34, 1, 1, "", "LightDarkViz"]], "pomdp_problems.light_dark.env.visual.LightDarkViz": [[34, 3, 1, "", "log_position"], [34, 3, 1, "", "plot"], [34, 3, 1, "", "set_goal"], [34, 3, 1, "", "set_initial_belief_pos"]], "pomdp_problems.light_dark.models": [[35, 0, 0, "-", "observation_model"], [35, 0, 0, "-", "transition_model"]], "pomdp_problems.light_dark.models.observation_model": [[35, 1, 1, "", "ObservationModel"]], "pomdp_problems.light_dark.models.observation_model.ObservationModel": [[35, 3, 1, "", "argmax"], [35, 3, 1, "", "func"], [35, 3, 1, "", "func_noise"], [35, 3, 1, "", "jac_dx"], [35, 3, 1, "", "noise_covariance"], [35, 3, 1, "", "probability"], [35, 3, 1, "", "sample"]], "pomdp_problems.light_dark.models.transition_model": [[35, 1, 1, "", "TransitionModel"]], "pomdp_problems.light_dark.models.transition_model.TransitionModel": [[35, 3, 1, "", "argmax"], [35, 3, 1, "", "func"], [35, 3, 1, "", "func_noise"], [35, 3, 1, "", "jac_du"], [35, 3, 1, "", "jac_dx"], [35, 3, 1, "", "probability"], [35, 3, 1, "", "sample"]], "pomdp_problems.light_dark.problem_discrete": [[31, 1, 1, "", "DiscreteLightDark"]], "pomdp_problems.load_unload": [[36, 0, 0, "-", "load_unload"]], "pomdp_problems.load_unload.load_unload": [[36, 1, 1, "", "LUAction"], [36, 1, 1, "", "LUObservation"], [36, 1, 1, "", "LUObservationModel"], [36, 1, 1, "", "LUPolicyModel"], [36, 1, 1, "", "LURewardModel"], [36, 1, 1, "", "LUState"], [36, 1, 1, "", "LUTransitionModel"], [36, 1, 1, "", "LoadUnloadProblem"], [36, 5, 1, "", "generate_init_belief"], [36, 5, 1, "", "generate_random_state"], [36, 5, 1, "", "main"], [36, 5, 1, "", "test_planner"]], "pomdp_problems.load_unload.load_unload.LUObservationModel": [[36, 3, 1, "", "argmax"], [36, 3, 1, "", "probability"], [36, 3, 1, "", "sample"]], "pomdp_problems.load_unload.load_unload.LUPolicyModel": [[36, 3, 1, "", "argmax"], [36, 3, 1, "", "get_all_actions"], [36, 3, 1, "", "probability"], [36, 3, 1, "", "sample"]], "pomdp_problems.load_unload.load_unload.LURewardModel": [[36, 3, 1, "", "argmax"], [36, 3, 1, "", "probability"], [36, 3, 1, "", "sample"]], "pomdp_problems.load_unload.load_unload.LUTransitionModel": [[36, 3, 1, "", "argmax"], [36, 3, 1, "", "probability"], [36, 3, 1, "", "sample"]], "pomdp_problems.maze": [[38, 0, 0, "-", "domain"], [39, 0, 0, "-", "env"], [40, 0, 0, "-", "models"]], "pomdp_problems.maze.domain": [[38, 0, 0, "-", "action"], [38, 0, 0, "-", "observation"], [38, 0, 0, "-", "state"]], "pomdp_problems.maze.domain.observation": [[38, 1, 1, "", "Observation"]], "pomdp_problems.maze.domain.state": [[38, 1, 1, "", "State"]], "pomdp_problems.maze.env": [[39, 0, 0, "-", "env"]], "pomdp_problems.maze.env.env": [[39, 1, 1, "", "MazeEnvironment"]], "pomdp_problems.maze.models": [[41, 0, 0, "-", "components"]], "pomdp_problems.multi_object_search.agent": [[43, 0, 0, "-", "agent"], [43, 0, 0, "-", "belief"]], "pomdp_problems.multi_object_search.agent.agent": [[43, 1, 1, "", "MosAgent"]], "pomdp_problems.multi_object_search.agent.agent.MosAgent": [[43, 3, 1, "", "clear_history"]], "pomdp_problems.multi_object_search.agent.belief": [[43, 1, 1, "", "MosOOBelief"], [43, 5, 1, "", "initialize_belief"]], "pomdp_problems.multi_object_search.agent.belief.MosOOBelief": [[43, 3, 1, "", "mpe"], [43, 3, 1, "", "random"]], "pomdp_problems.multi_object_search.domain": [[44, 0, 0, "-", "action"], [44, 0, 0, "-", "observation"], [44, 0, 0, "-", "state"]], "pomdp_problems.multi_object_search.domain.action": [[44, 1, 1, "", "Action"], [44, 1, 1, "", "FindAction"], [44, 1, 1, "", "LookAction"], [44, 1, 1, "", "MotionAction"]], "pomdp_problems.multi_object_search.domain.action.MotionAction": [[44, 2, 1, "", "BACKWARD"], [44, 2, 1, "", "EAST"], [44, 2, 1, "", "EAST2D"], [44, 2, 1, "", "FORWARD"], [44, 2, 1, "", "LEFT"], [44, 2, 1, "", "NORTH"], [44, 2, 1, "", "NORTH2D"], [44, 2, 1, "", "RIGHT"], [44, 2, 1, "", "SCHEMES"], [44, 2, 1, "", "SCHEME_VW"], [44, 2, 1, "", "SCHEME_XY"], [44, 2, 1, "", "SCHEME_XYTH"], [44, 2, 1, "", "SOUTH"], [44, 2, 1, "", "SOUTH2D"], [44, 2, 1, "", "WEST"], [44, 2, 1, "", "WEST2D"]], "pomdp_problems.multi_object_search.domain.observation": [[44, 1, 1, "", "MosOOObservation"], [44, 1, 1, "", "ObjectObservation"]], "pomdp_problems.multi_object_search.domain.observation.MosOOObservation": [[44, 3, 1, "", "factor"], [44, 3, 1, "", "for_obj"], [44, 3, 1, "", "merge"]], "pomdp_problems.multi_object_search.domain.observation.ObjectObservation": [[44, 2, 1, "", "NULL"]], "pomdp_problems.multi_object_search.domain.state": [[44, 1, 1, "", "MosOOState"], [44, 1, 1, "", "ObjectState"], [44, 1, 1, "", "RobotState"]], "pomdp_problems.multi_object_search.domain.state.MosOOState": [[44, 3, 1, "", "object_pose"], [44, 4, 1, "", "object_poses"], [44, 3, 1, "", "pose"]], "pomdp_problems.multi_object_search.domain.state.ObjectState": [[44, 4, 1, "", "objid"], [44, 4, 1, "", "pose"]], "pomdp_problems.multi_object_search.domain.state.RobotState": [[44, 4, 1, "", "objects_found"], [44, 4, 1, "", "pose"], [44, 4, 1, "", "robot_pose"]], "pomdp_problems.multi_object_search.env": [[45, 0, 0, "-", "env"], [45, 0, 0, "-", "visual"]], "pomdp_problems.multi_object_search.env.env": [[45, 1, 1, "", "MosEnvironment"], [45, 5, 1, "", "equip_sensors"], [45, 5, 1, "", "interpret"], [45, 5, 1, "", "interpret_robot_id"], [45, 5, 1, "", "make_laser_sensor"], [45, 5, 1, "", "make_proximity_sensor"]], "pomdp_problems.multi_object_search.env.env.MosEnvironment": [[45, 4, 1, "", "robot_ids"], [45, 3, 1, "", "state_transition"]], "pomdp_problems.multi_object_search.env.visual": [[45, 1, 1, "", "MosViz"], [45, 5, 1, "", "object_color"], [45, 5, 1, "", "unittest"]], "pomdp_problems.multi_object_search.env.visual.MosViz": [[45, 3, 1, "", "draw_belief"], [45, 3, 1, "", "draw_observation"], [45, 3, 1, "", "draw_robot"], [45, 4, 1, "", "img_height"], [45, 4, 1, "", "img_width"], [45, 4, 1, "", "last_observation"], [45, 3, 1, "", "on_cleanup"], [45, 3, 1, "", "on_event"], [45, 3, 1, "", "on_execute"], [45, 3, 1, "", "on_init"], [45, 3, 1, "", "on_loop"], [45, 3, 1, "", "on_render"], [45, 3, 1, "", "render_env"], [45, 3, 1, "", "update"]], "pomdp_problems.multi_object_search": [[42, 0, 0, "-", "example_worlds"], [42, 0, 0, "-", "problem"]], "pomdp_problems.multi_object_search.example_worlds": [[42, 5, 1, "", "random_world"]], "pomdp_problems.multi_object_search.models": [[47, 0, 0, "-", "components"], [46, 0, 0, "-", "observation_model"], [46, 0, 0, "-", "policy_model"], [46, 0, 0, "-", "reward_model"], [46, 0, 0, "-", "transition_model"]], "pomdp_problems.multi_object_search.models.components": [[47, 0, 0, "-", "grid_map"], [47, 0, 0, "-", "sensor"]], "pomdp_problems.multi_object_search.models.components.grid_map": [[47, 1, 1, "", "GridMap"]], "pomdp_problems.multi_object_search.models.components.grid_map.GridMap": [[47, 3, 1, "", "valid_motions"]], "pomdp_problems.multi_object_search.models.components.sensor": [[47, 1, 1, "", "Laser2DSensor"], [47, 1, 1, "", "ProximitySensor"], [47, 1, 1, "", "Sensor"], [47, 5, 1, "", "euclidean_dist"], [47, 5, 1, "", "in_range"], [47, 5, 1, "", "to_rad"]], "pomdp_problems.multi_object_search.models.components.sensor.Laser2DSensor": [[47, 3, 1, "", "in_field_of_view"], [47, 3, 1, "", "observe"], [47, 4, 1, "", "sensing_region_size"], [47, 3, 1, "", "shoot_beam"], [47, 3, 1, "", "valid_beam"], [47, 3, 1, "", "within_range"]], "pomdp_problems.multi_object_search.models.components.sensor.Sensor": [[47, 2, 1, "", "LASER"], [47, 2, 1, "", "PROXIMITY"], [47, 3, 1, "", "observe"], [47, 4, 1, "", "robot_id"], [47, 4, 1, "", "sensing_region_size"], [47, 3, 1, "", "within_range"]], "pomdp_problems.multi_object_search.models.observation_model": [[46, 1, 1, "", "MosObservationModel"], [46, 1, 1, "", "ObjectObservationModel"], [46, 5, 1, "", "unittest"]], "pomdp_problems.multi_object_search.models.observation_model.MosObservationModel": [[46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.models.observation_model.ObjectObservationModel": [[46, 3, 1, "", "argmax"], [46, 3, 1, "", "probability"], [46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.models.policy_model": [[46, 1, 1, "", "PolicyModel"]], "pomdp_problems.multi_object_search.models.policy_model.PolicyModel": [[46, 3, 1, "", "argmax"], [46, 3, 1, "", "get_all_actions"], [46, 3, 1, "", "probability"], [46, 3, 1, "", "rollout"], [46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.models.reward_model": [[46, 1, 1, "", "GoalRewardModel"], [46, 1, 1, "", "MosRewardModel"]], "pomdp_problems.multi_object_search.models.reward_model.MosRewardModel": [[46, 3, 1, "", "argmax"], [46, 3, 1, "", "probability"], [46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.models.transition_model": [[46, 1, 1, "", "MosTransitionModel"], [46, 1, 1, "", "RobotTransitionModel"], [46, 1, 1, "", "StaticObjectTransitionModel"], [46, 5, 1, "", "in_boundary"], [46, 5, 1, "", "valid_pose"]], "pomdp_problems.multi_object_search.models.transition_model.MosTransitionModel": [[46, 3, 1, "", "argmax"], [46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.models.transition_model.RobotTransitionModel": [[46, 3, 1, "", "argmax"], [46, 3, 1, "", "if_move_by"], [46, 3, 1, "", "probability"], [46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.models.transition_model.StaticObjectTransitionModel": [[46, 3, 1, "", "argmax"], [46, 3, 1, "", "probability"], [46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.problem": [[42, 1, 1, "", "MosOOPOMDP"], [42, 5, 1, "", "belief_update"], [42, 5, 1, "", "solve"], [42, 5, 1, "", "unittest"]], "pomdp_problems.rocksample": [[49, 0, 0, "-", "cythonize"], [48, 0, 0, "module-0", "rocksample_problem"]], "pomdp_problems.rocksample.cythonize": [[49, 0, 0, "-", "rocksample_problem"]], "pomdp_problems.rocksample.cythonize.rocksample_problem": [[49, 1, 1, "", "CheckAction"], [49, 1, 1, "", "MoveAction"], [49, 1, 1, "", "RSAction"], [49, 1, 1, "", "RSObservation"], [49, 1, 1, "", "RSObservationModel"], [49, 1, 1, "", "RSPolicyModel"], [49, 1, 1, "", "RSRewardModel"], [49, 1, 1, "", "RSState"], [49, 1, 1, "", "RSTransitionModel"], [49, 1, 1, "", "RockSampleProblem"], [49, 1, 1, "", "RockType"], [49, 1, 1, "", "SampleAction"], [49, 5, 1, "", "euclidean_dist"], [49, 5, 1, "", "init_particles_belief"], [49, 5, 1, "", "main"], [49, 5, 1, "", "test_planner"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.CheckAction": [[49, 2, 1, "", "rock_id"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction": [[49, 2, 1, "", "EAST"], [49, 2, 1, "", "NORTH"], [49, 2, 1, "", "SOUTH"], [49, 2, 1, "", "WEST"], [49, 2, 1, "", "motion"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservation": [[49, 2, 1, "", "quality"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservationModel": [[49, 3, 1, "", "argmax"], [49, 3, 1, "", "probability"], [49, 3, 1, "", "sample"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel": [[49, 3, 1, "", "argmax"], [49, 3, 1, "", "get_all_actions"], [49, 3, 1, "", "probability"], [49, 3, 1, "", "rollout"], [49, 3, 1, "", "sample"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RSRewardModel": [[49, 3, 1, "", "argmax"], [49, 3, 1, "", "probability"], [49, 3, 1, "", "sample"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RSState": [[49, 2, 1, "", "position"], [49, 2, 1, "", "rocktypes"], [49, 2, 1, "", "terminal"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RSTransitionModel": [[49, 3, 1, "", "argmax"], [49, 3, 1, "", "probability"], [49, 3, 1, "", "sample"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RockSampleProblem": [[49, 3, 1, "", "generate_instance"], [49, 3, 1, "", "in_exit_area"], [49, 3, 1, "", "print_state"], [49, 3, 1, "", "random_free_location"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RockType": [[49, 2, 1, "", "BAD"], [49, 2, 1, "", "GOOD"], [49, 3, 1, "", "invert"], [49, 3, 1, "", "random"]], "pomdp_problems.rocksample.rocksample_problem": [[48, 1, 1, "id8", "Action"], [48, 1, 1, "id15", "CheckAction"], [48, 1, 1, "id9", "MoveAction"], [48, 1, 1, "id16", "Observation"], [48, 1, 1, "id21", "RSObservationModel"], [48, 1, 1, "id29", "RSPolicyModel"], [48, 1, 1, "id25", "RSRewardModel"], [48, 1, 1, "id17", "RSTransitionModel"], [48, 1, 1, "id35", "RockSampleProblem"], [48, 1, 1, "id2", "RockType"], [48, 1, 1, "id14", "SampleAction"], [48, 1, 1, "id7", "State"], [48, 5, 1, "id0", "euclidean_dist"], [48, 5, 1, "id41", "init_particles_belief"], [48, 5, 1, "id42", "main"], [48, 5, 1, "id40", "test_planner"]], "pomdp_problems.rocksample.rocksample_problem.MoveAction": [[48, 2, 1, "id10", "EAST"], [48, 2, 1, "id12", "NORTH"], [48, 2, 1, "id13", "SOUTH"], [48, 2, 1, "id11", "WEST"]], "pomdp_problems.rocksample.rocksample_problem.RSObservationModel": [[48, 3, 1, "id24", "argmax"], [48, 3, 1, "id22", "probability"], [48, 3, 1, "id23", "sample"]], "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel": [[48, 3, 1, "id32", "argmax"], [48, 3, 1, "id33", "get_all_actions"], [48, 3, 1, "id31", "probability"], [48, 3, 1, "id34", "rollout"], [48, 3, 1, "id30", "sample"]], "pomdp_problems.rocksample.rocksample_problem.RSRewardModel": [[48, 3, 1, "id27", "argmax"], [48, 3, 1, "id28", "probability"], [48, 3, 1, "id26", "sample"]], "pomdp_problems.rocksample.rocksample_problem.RSTransitionModel": [[48, 3, 1, "id20", "argmax"], [48, 3, 1, "id18", "probability"], [48, 3, 1, "id19", "sample"]], "pomdp_problems.rocksample.rocksample_problem.RockSampleProblem": [[48, 3, 1, "id38", "generate_instance"], [48, 3, 1, "id37", "in_exit_area"], [48, 3, 1, "id39", "print_state"], [48, 3, 1, "id36", "random_free_location"]], "pomdp_problems.rocksample.rocksample_problem.RockType": [[48, 2, 1, "id4", "BAD"], [48, 2, 1, "id3", "GOOD"], [48, 3, 1, "id5", "invert"], [48, 3, 1, "id6", "random"]], "pomdp_problems.tag": [[51, 0, 0, "-", "agent"], [50, 0, 0, "-", "constants"], [52, 0, 0, "-", "domain"], [53, 0, 0, "-", "env"], [50, 0, 0, "-", "example_worlds"], [50, 0, 0, "-", "experiment"], [54, 0, 0, "-", "models"], [50, 0, 0, "-", "problem"]], "pomdp_problems.tag.agent": [[51, 0, 0, "-", "agent"]], "pomdp_problems.tag.agent.agent": [[51, 1, 1, "", "TagAgent"], [51, 5, 1, "", "belief_update"], [51, 5, 1, "", "initialize_belief"], [51, 5, 1, "", "initialize_particles_belief"]], "pomdp_problems.tag.agent.agent.TagAgent": [[51, 3, 1, "", "clear_history"]], "pomdp_problems.tag.domain": [[52, 0, 0, "-", "action"], [52, 0, 0, "-", "observation"], [52, 0, 0, "-", "state"]], "pomdp_problems.tag.domain.action": [[52, 1, 1, "", "TagAction"]], "pomdp_problems.tag.domain.observation": [[52, 1, 1, "", "TagObservation"]], "pomdp_problems.tag.domain.state": [[52, 1, 1, "", "TagState"]], "pomdp_problems.tag.env": [[53, 0, 0, "-", "env"], [53, 0, 0, "-", "visual"]], "pomdp_problems.tag.env.env": [[53, 1, 1, "", "TagEnvironment"]], "pomdp_problems.tag.env.env.TagEnvironment": [[53, 3, 1, "", "from_str"], [53, 4, 1, "", "grid_map"], [53, 4, 1, "", "length"], [53, 4, 1, "", "width"]], "pomdp_problems.tag.env.visual": [[53, 1, 1, "", "TagViz"], [53, 5, 1, "", "unittest"]], "pomdp_problems.tag.env.visual.TagViz": [[53, 3, 1, "", "draw_belief"], [53, 3, 1, "", "draw_observation"], [53, 3, 1, "", "draw_robot"], [53, 4, 1, "", "img_height"], [53, 4, 1, "", "img_width"], [53, 4, 1, "", "last_observation"], [53, 3, 1, "", "on_cleanup"], [53, 3, 1, "", "on_event"], [53, 3, 1, "", "on_execute"], [53, 3, 1, "", "on_init"], [53, 3, 1, "", "on_loop"], [53, 3, 1, "", "on_render"], [53, 3, 1, "", "render_env"], [53, 3, 1, "", "update"]], "pomdp_problems.tag.experiment": [[50, 5, 1, "", "main"], [50, 5, 1, "", "trial"]], "pomdp_problems.tag.models": [[55, 0, 0, "-", "components"], [54, 0, 0, "-", "observation_model"], [54, 0, 0, "-", "policy_model"], [54, 0, 0, "-", "reward_model"], [54, 0, 0, "-", "transition_model"]], "pomdp_problems.tag.models.components": [[55, 0, 0, "-", "grid_map"], [55, 0, 0, "-", "motion_policy"]], "pomdp_problems.tag.models.components.grid_map": [[55, 1, 1, "", "GridMap"]], "pomdp_problems.tag.models.components.grid_map.GridMap": [[55, 3, 1, "", "free_cells"], [55, 3, 1, "", "from_str"], [55, 3, 1, "", "valid_motions"], [55, 3, 1, "", "valid_pose"]], "pomdp_problems.tag.models.components.motion_policy": [[55, 1, 1, "", "TagTargetMotionPolicy"]], "pomdp_problems.tag.models.components.motion_policy.TagTargetMotionPolicy": [[55, 3, 1, "", "mpe"], [55, 3, 1, "", "probability"], [55, 3, 1, "", "random"]], "pomdp_problems.tag.models.observation_model": [[54, 1, 1, "", "TagObservationModel"]], "pomdp_problems.tag.models.observation_model.TagObservationModel": [[54, 3, 1, "", "argmax"], [54, 3, 1, "", "probability"], [54, 3, 1, "", "sample"]], "pomdp_problems.tag.models.policy_model": [[54, 1, 1, "", "TagPolicyModel"]], "pomdp_problems.tag.models.policy_model.TagPolicyModel": [[54, 3, 1, "", "get_all_actions"], [54, 3, 1, "", "rollout"], [54, 3, 1, "", "sample"]], "pomdp_problems.tag.models.reward_model": [[54, 1, 1, "", "TagRewardModel"]], "pomdp_problems.tag.models.reward_model.TagRewardModel": [[54, 3, 1, "", "probability"], [54, 3, 1, "", "sample"]], "pomdp_problems.tag.models.transition_model": [[54, 1, 1, "", "TagTransitionModel"]], "pomdp_problems.tag.models.transition_model.TagTransitionModel": [[54, 3, 1, "", "argmax"], [54, 3, 1, "", "if_move_by"], [54, 3, 1, "", "probability"], [54, 3, 1, "", "sample"]], "pomdp_problems.tag.problem": [[50, 1, 1, "", "TagProblem"], [50, 5, 1, "", "main"], [50, 5, 1, "", "solve"]], "pomdp_problems.tiger": [[57, 0, 0, "-", "cythonize"], [56, 0, 0, "-", "tiger_problem"]], "pomdp_problems.tiger.cythonize": [[57, 0, 0, "-", "tiger_problem"]], "pomdp_problems.tiger.cythonize.tiger_problem": [[57, 1, 1, "", "TigerAction"], [57, 1, 1, "", "TigerObservation"], [57, 1, 1, "", "TigerObservationModel"], [57, 1, 1, "", "TigerPolicyModel"], [57, 1, 1, "", "TigerProblem"], [57, 1, 1, "", "TigerRewardModel"], [57, 1, 1, "", "TigerState"], [57, 1, 1, "", "TigerTransitionModel"], [57, 5, 1, "", "build_actions"], [57, 5, 1, "", "build_observations"], [57, 5, 1, "", "build_setting"], [57, 5, 1, "", "build_states"], [57, 5, 1, "", "main"], [57, 5, 1, "", "test_planner"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservation": [[57, 2, 1, "", "name"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel": [[57, 3, 1, "", "argmax"], [57, 3, 1, "", "get_all_observations"], [57, 3, 1, "", "get_distribution"], [57, 3, 1, "", "probability"], [57, 3, 1, "", "sample"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerPolicyModel": [[57, 3, 1, "", "argmax"], [57, 3, 1, "", "get_all_actions"], [57, 3, 1, "", "probability"], [57, 3, 1, "", "sample"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerProblem": [[57, 2, 1, "", "ACTIONS"], [57, 2, 1, "", "OBSERVATIONS"], [57, 2, 1, "", "STATES"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerRewardModel": [[57, 3, 1, "", "argmax"], [57, 3, 1, "", "get_distribution"], [57, 3, 1, "", "probability"], [57, 3, 1, "", "sample"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerState": [[57, 2, 1, "", "name"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel": [[57, 3, 1, "", "argmax"], [57, 3, 1, "", "get_all_states"], [57, 3, 1, "", "get_distribution"], [57, 3, 1, "", "probability"], [57, 3, 1, "", "sample"]], "pomdp_problems.tiger.tiger_problem": [[56, 1, 1, "", "ObservationModel"], [56, 1, 1, "", "PolicyModel"], [56, 1, 1, "", "RewardModel"], [56, 1, 1, "", "TigerAction"], [56, 1, 1, "", "TigerObservation"], [56, 1, 1, "", "TigerProblem"], [56, 1, 1, "", "TigerState"], [56, 1, 1, "", "TransitionModel"], [56, 5, 1, "", "main"], [56, 5, 1, "", "test_planner"]], "pomdp_problems.tiger.tiger_problem.ObservationModel": [[56, 3, 1, "", "get_all_observations"], [56, 3, 1, "", "probability"], [56, 3, 1, "", "sample"]], "pomdp_problems.tiger.tiger_problem.PolicyModel": [[56, 2, 1, "", "ACTIONS"], [56, 3, 1, "", "get_all_actions"], [56, 3, 1, "", "rollout"], [56, 3, 1, "", "sample"]], "pomdp_problems.tiger.tiger_problem.RewardModel": [[56, 3, 1, "", "sample"]], "pomdp_problems.tiger.tiger_problem.TigerProblem": [[56, 3, 1, "", "create"]], "pomdp_problems.tiger.tiger_problem.TigerState": [[56, 3, 1, "", "other"]], "pomdp_problems.tiger.tiger_problem.TransitionModel": [[56, 3, 1, "", "get_all_states"], [56, 3, 1, "", "probability"], [56, 3, 1, "", "sample"]], "pomdp_py.algorithms": [[3, 0, 0, "-", "bsp"], [2, 0, 0, "-", "po_rollout"], [2, 0, 0, "-", "po_uct"], [2, 0, 0, "-", "pomcp"], [2, 0, 0, "-", "value_iteration"]], "pomdp_py.algorithms.bsp": [[2, 0, 0, "-", "blqr"]], "pomdp_py.algorithms.bsp.blqr": [[2, 1, 1, "", "BLQR"]], "pomdp_py.algorithms.bsp.blqr.BLQR": [[2, 3, 1, "", "create_plan"], [2, 3, 1, "", "ekf_update_mlo"], [2, 3, 1, "", "integrate_belief_segment"], [2, 3, 1, "", "interpret_sqp_plan"], [2, 3, 1, "", "segmented_cost_function"]], "pomdp_py.algorithms.po_rollout": [[2, 1, 1, "", "PORollout"]], "pomdp_py.algorithms.po_rollout.PORollout": [[2, 3, 1, "", "clear_agent"], [2, 2, 1, "", "last_best_reward"], [2, 3, 1, "", "plan"], [2, 3, 1, "", "set_rollout_policy"], [2, 3, 1, "", "update"], [2, 2, 1, "", "update_agent_belief"]], "pomdp_py.algorithms.po_uct": [[2, 1, 1, "", "ActionPrior"], [2, 1, 1, "", "POUCT"], [2, 1, 1, "", "QNode"], [2, 1, 1, "", "RandomRollout"], [2, 1, 1, "", "RolloutPolicy"], [2, 1, 1, "", "RootVNode"], [2, 1, 1, "", "TreeNode"], [2, 1, 1, "", "VNode"]], "pomdp_py.algorithms.po_uct.ActionPrior": [[2, 3, 1, "", "get_preferred_actions"]], "pomdp_py.algorithms.po_uct.POUCT": [[2, 3, 1, "", "clear_agent"], [2, 2, 1, "", "last_num_sims"], [2, 2, 1, "", "last_planning_time"], [2, 3, 1, "", "plan"], [2, 3, 1, "", "set_rollout_policy"], [2, 3, 1, "", "update"], [2, 2, 1, "", "updates_agent_belief"]], "pomdp_py.algorithms.po_uct.RandomRollout": [[2, 3, 1, "", "rollout"]], "pomdp_py.algorithms.po_uct.RolloutPolicy": [[2, 3, 1, "", "rollout"]], "pomdp_py.algorithms.po_uct.RootVNode": [[2, 3, 1, "", "from_vnode"], [2, 2, 1, "", "history"]], "pomdp_py.algorithms.po_uct.TreeNode": [[2, 2, 1, "", "children"], [2, 2, 1, "", "num_visits"], [2, 2, 1, "", "value"]], "pomdp_py.algorithms.po_uct.VNode": [[2, 3, 1, "", "argmax"], [2, 3, 1, "", "print_children_value"], [2, 2, 1, "", "value"]], "pomdp_py.algorithms.pomcp": [[2, 1, 1, "", "POMCP"], [2, 1, 1, "", "RootVNodeParticles"], [2, 1, 1, "", "VNodeParticles"]], "pomdp_py.algorithms.pomcp.POMCP": [[2, 3, 1, "", "plan"], [2, 3, 1, "", "update"], [2, 2, 1, "", "update_agent_belief"]], "pomdp_py.algorithms.pomcp.RootVNodeParticles": [[2, 2, 1, "", "belief"], [2, 3, 1, "", "from_vnode"]], "pomdp_py.algorithms.pomcp.VNodeParticles": [[2, 2, 1, "", "belief"]], "pomdp_py.algorithms.value_iteration": [[2, 1, 1, "", "ValueIteration"]], "pomdp_py.algorithms.value_iteration.ValueIteration": [[2, 3, 1, "", "plan"]], "pomdp_py.framework": [[5, 0, 0, "-", "basics"], [5, 0, 0, "-", "oopomdp"], [5, 0, 0, "-", "planner"]], "pomdp_py.framework.basics": [[5, 1, 1, "", "Action"], [5, 1, 1, "", "Agent"], [5, 1, 1, "", "BlackboxModel"], [5, 1, 1, "", "Distribution"], [5, 1, 1, "", "Environment"], [5, 1, 1, "", "GenerativeDistribution"], [5, 1, 1, "", "Observation"], [5, 1, 1, "", "ObservationModel"], [5, 1, 1, "", "Option"], [5, 1, 1, "", "POMDP"], [5, 1, 1, "", "PolicyModel"], [5, 1, 1, "", "RewardModel"], [5, 1, 1, "", "State"], [5, 1, 1, "", "TransitionModel"], [5, 5, 1, "", "sample_explict_models"], [5, 5, 1, "", "sample_generative_model"]], "pomdp_py.framework.basics.Agent": [[5, 3, 1, "", "add_attr"], [5, 2, 1, "", "all_actions"], [5, 2, 1, "", "all_observations"], [5, 2, 1, "", "all_states"], [5, 2, 1, "", "belief"], [5, 2, 1, "", "history"], [5, 2, 1, "", "init_belief"], [5, 3, 1, "", "sample_belief"], [5, 3, 1, "", "set_belief"], [5, 3, 1, "", "update"], [5, 3, 1, "", "update_history"]], "pomdp_py.framework.basics.BlackboxModel": [[5, 3, 1, "", "argmax"], [5, 3, 1, "", "sample"]], "pomdp_py.framework.basics.Distribution": [[5, 3, 1, "", "__getitem__"], [5, 3, 1, "", "__setitem__"]], "pomdp_py.framework.basics.Environment": [[5, 3, 1, "", "apply_transition"], [5, 2, 1, "", "blackbox_model"], [5, 2, 1, "", "cur_state"], [5, 3, 1, "", "provide_observation"], [5, 2, 1, "", "reward_model"], [5, 2, 1, "", "state"], [5, 3, 1, "", "state_transition"], [5, 2, 1, "", "transition_model"]], "pomdp_py.framework.basics.GenerativeDistribution": [[5, 3, 1, "", "argmax"], [5, 3, 1, "", "get_histogram"], [5, 3, 1, "", "mpe"]], "pomdp_py.framework.basics.ObservationModel": [[5, 3, 1, "", "argmax"], [5, 3, 1, "", "get_all_observations"], [5, 3, 1, "", "get_distribution"], [5, 3, 1, "", "probability"], [5, 3, 1, "", "sample"]], "pomdp_py.framework.basics.Option": [[5, 3, 1, "", "initiation"], [5, 2, 1, "", "policy"], [5, 3, 1, "", "sample"], [5, 3, 1, "", "termination"]], "pomdp_py.framework.basics.PolicyModel": [[5, 3, 1, "", "argmax"], [5, 3, 1, "", "get_all_actions"], [5, 3, 1, "", "get_distribution"], [5, 3, 1, "", "probability"], [5, 3, 1, "", "sample"], [5, 3, 1, "", "update"]], "pomdp_py.framework.basics.RewardModel": [[5, 3, 1, "", "argmax"], [5, 3, 1, "", "get_distribution"], [5, 3, 1, "", "probability"], [5, 3, 1, "", "sample"]], "pomdp_py.framework.basics.TransitionModel": [[5, 3, 1, "", "argmax"], [5, 3, 1, "", "get_all_states"], [5, 3, 1, "", "get_distribution"], [5, 3, 1, "", "probability"], [5, 3, 1, "", "sample"]], "pomdp_py.framework.oopomdp": [[5, 1, 1, "", "OOBelief"], [5, 1, 1, "", "OOObservation"], [5, 1, 1, "", "OOObservationModel"], [5, 1, 1, "", "OOPOMDP"], [5, 1, 1, "", "OOState"], [5, 1, 1, "", "OOTransitionModel"], [5, 1, 1, "", "ObjectState"]], "pomdp_py.framework.oopomdp.OOBelief": [[5, 3, 1, "", "__getitem__"], [5, 3, 1, "", "__setitem__"], [5, 3, 1, "", "b"], [5, 3, 1, "", "mpe"], [5, 3, 1, "", "object_belief"], [5, 2, 1, "", "object_beliefs"], [5, 3, 1, "", "random"], [5, 3, 1, "", "set_object_belief"]], "pomdp_py.framework.oopomdp.OOObservation": [[5, 3, 1, "", "factor"], [5, 3, 1, "", "merge"]], "pomdp_py.framework.oopomdp.OOObservationModel": [[5, 3, 1, "", "__getitem__"], [5, 3, 1, "", "argmax"], [5, 2, 1, "", "observation_models"], [5, 3, 1, "", "probability"], [5, 3, 1, "", "sample"]], "pomdp_py.framework.oopomdp.OOState": [[5, 3, 1, "", "__getitem__"], [5, 3, 1, "", "copy"], [5, 3, 1, "", "get_object_attribute"], [5, 3, 1, "", "get_object_class"], [5, 3, 1, "", "get_object_state"], [5, 3, 1, "", "s"], [5, 3, 1, "", "set_object_state"], [5, 2, 1, "", "situation"]], "pomdp_py.framework.oopomdp.OOTransitionModel": [[5, 3, 1, "", "__getitem__"], [5, 3, 1, "", "argmax"], [5, 3, 1, "", "probability"], [5, 3, 1, "", "sample"], [5, 2, 1, "", "transition_models"]], "pomdp_py.framework.oopomdp.ObjectState": [[5, 3, 1, "", "__getitem__"], [5, 3, 1, "", "__setitem__"], [5, 3, 1, "", "copy"]], "pomdp_py.framework.planner": [[5, 1, 1, "", "Planner"]], "pomdp_py.framework.planner.Planner": [[5, 3, 1, "", "plan"], [5, 3, 1, "", "update"], [5, 3, 1, "", "updates_agent_belief"]], "pomdp_py.representations.belief": [[7, 0, 0, "-", "histogram"], [7, 0, 0, "-", "particles"]], "pomdp_py.representations.belief.histogram": [[7, 5, 1, "", "abstraction_over_histogram"], [7, 5, 1, "", "update_histogram_belief"]], "pomdp_py.representations.belief.particles": [[7, 5, 1, "", "abstraction_over_particles"], [7, 5, 1, "", "particle_reinvigoration"], [7, 5, 1, "", "update_particles_belief"]], "pomdp_py.representations.distribution": [[8, 0, 0, "-", "gaussian"], [8, 0, 0, "-", "histogram"], [8, 0, 0, "-", "particles"]], "pomdp_py.representations.distribution.gaussian": [[8, 1, 1, "", "Gaussian"]], "pomdp_py.representations.distribution.gaussian.Gaussian": [[8, 3, 1, "", "__getitem__"], [8, 3, 1, "", "__setitem__"], [8, 2, 1, "", "cov"], [8, 2, 1, "", "covariance"], [8, 2, 1, "", "mean"], [8, 3, 1, "", "mpe"], [8, 3, 1, "", "random"], [8, 2, 1, "", "sigma"]], "pomdp_py.representations.distribution.histogram": [[8, 1, 1, "", "Histogram"]], "pomdp_py.representations.distribution.histogram.Histogram": [[8, 3, 1, "", "__getitem__"], [8, 3, 1, "", "__setitem__"], [8, 3, 1, "", "get_histogram"], [8, 2, 1, "", "histogram"], [8, 3, 1, "", "is_normalized"], [8, 3, 1, "", "mpe"], [8, 3, 1, "", "random"]], "pomdp_py.representations.distribution.particles": [[8, 1, 1, "", "Particles"], [8, 1, 1, "", "WeightedParticles"]], "pomdp_py.representations.distribution.particles.Particles": [[8, 3, 1, "", "add"], [8, 3, 1, "", "from_histogram"], [8, 3, 1, "", "get_abstraction"], [8, 3, 1, "", "get_histogram"], [8, 2, 1, "", "particles"], [8, 3, 1, "", "random"]], "pomdp_py.representations.distribution.particles.WeightedParticles": [[8, 3, 1, "", "__getitem__"], [8, 3, 1, "", "__setitem__"], [8, 3, 1, "", "add"], [8, 3, 1, "", "condense"], [8, 3, 1, "", "from_histogram"], [8, 3, 1, "", "get_histogram"], [8, 3, 1, "", "mpe"], [8, 2, 1, "", "particles"], [8, 3, 1, "", "random"], [8, 2, 1, "", "values"], [8, 2, 1, "", "weights"]], "pomdp_py": [[9, 0, 0, "-", "utils"], [12, 0, 0, "-", "visual"]], "pomdp_py.utils": [[9, 0, 0, "-", "colors"], [9, 0, 0, "-", "cython_utils"], [9, 0, 0, "-", "debugging"], [9, 0, 0, "-", "math"], [9, 0, 0, "-", "misc"], [9, 0, 0, "-", "plotting"], [9, 0, 0, "-", "templates"], [9, 0, 0, "-", "test_utils"], [9, 0, 0, "-", "typ"]], "pomdp_py.utils.colors": [[9, 5, 1, "", "hex_to_rgb"], [9, 5, 1, "", "inverse_color_hex"], [9, 5, 1, "", "inverse_color_rgb"], [9, 5, 1, "", "lighter"], [9, 5, 1, "", "random_unique_color"], [9, 5, 1, "", "rgb_to_hex"]], "pomdp_py.utils.cython_utils": [[9, 5, 1, "", "det_dict_hash"]], "pomdp_py.utils.debugging": [[9, 1, 1, "", "TreeDebugger"], [9, 5, 1, "", "interpret_color"], [9, 5, 1, "", "sorted_by_str"]], "pomdp_py.utils.debugging.TreeDebugger": [[9, 4, 1, "", "b"], [9, 3, 1, "", "back"], [9, 4, 1, "", "bestseq"], [9, 3, 1, "", "bestseqd"], [9, 4, 1, "", "c"], [9, 4, 1, "", "clear"], [9, 4, 1, "", "d"], [9, 4, 1, "", "depth"], [9, 3, 1, "", "l"], [9, 3, 1, "", "layer"], [9, 4, 1, "", "leaf"], [9, 3, 1, "", "mark"], [9, 3, 1, "", "mark_path"], [9, 3, 1, "", "mark_sequence"], [9, 3, 1, "", "markp"], [9, 4, 1, "", "mbp"], [9, 4, 1, "", "nl"], [9, 4, 1, "", "nn"], [9, 4, 1, "", "nq"], [9, 4, 1, "", "num_layers"], [9, 3, 1, "", "num_nodes"], [9, 4, 1, "", "nv"], [9, 3, 1, "", "p"], [9, 3, 1, "", "path"], [9, 3, 1, "", "path_to"], [9, 4, 1, "", "pm"], [9, 4, 1, "", "pp"], [9, 3, 1, "", "preferred_actions"], [9, 4, 1, "", "r"], [9, 4, 1, "", "root"], [9, 3, 1, "", "s"], [9, 3, 1, "", "single_node_str"], [9, 3, 1, "", "step"], [9, 3, 1, "", "tree_stats"]], "pomdp_py.utils.interfaces.conversion": [[18, 1, 1, "", "AlphaVectorPolicy"], [18, 1, 1, "", "PolicyGraph"], [18, 5, 1, "", "to_pomdp_file"], [18, 5, 1, "", "to_pomdpx_file"]], "pomdp_py.utils.interfaces.conversion.AlphaVectorPolicy": [[18, 3, 1, "", "construct"], [18, 3, 1, "", "plan"], [18, 3, 1, "", "value"]], "pomdp_py.utils.interfaces.conversion.PolicyGraph": [[18, 3, 1, "", "construct"], [18, 3, 1, "", "plan"], [18, 3, 1, "", "update"]], "pomdp_py.utils.interfaces": [[18, 0, 0, "-", "solvers"]], "pomdp_py.utils.interfaces.solvers": [[18, 5, 1, "", "sarsop"], [18, 5, 1, "", "vi_pruning"]], "pomdp_py.utils.math": [[9, 5, 1, "", "R_between"], [9, 5, 1, "", "R_x"], [9, 5, 1, "", "R_y"], [9, 5, 1, "", "R_z"], [9, 5, 1, "", "T"], [9, 5, 1, "", "approx_equal"], [9, 5, 1, "", "euclidean_dist"], [9, 5, 1, "", "proj"], [9, 5, 1, "", "to_radians"], [9, 5, 1, "", "vec"]], "pomdp_py.utils.misc": [[9, 5, 1, "", "json_safe"], [9, 5, 1, "", "remap"], [9, 5, 1, "", "safe_slice"], [9, 5, 1, "", "similar"], [9, 1, 1, "", "special_char"]], "pomdp_py.utils.misc.special_char": [[9, 2, 1, "", "SUBSCRIPT"], [9, 2, 1, "", "bottomleft"], [9, 2, 1, "", "bottomright"], [9, 2, 1, "", "bottomt"], [9, 2, 1, "", "down"], [9, 2, 1, "", "hline"], [9, 2, 1, "", "intersect"], [9, 2, 1, "", "left"], [9, 2, 1, "", "leftt"], [9, 2, 1, "", "longbottomleft"], [9, 2, 1, "", "longbottomright"], [9, 2, 1, "", "longleft"], [9, 2, 1, "", "longright"], [9, 2, 1, "", "longtopleft"], [9, 2, 1, "", "longtopright"], [9, 2, 1, "", "right"], [9, 2, 1, "", "rightt"], [9, 2, 1, "", "shadebar"], [9, 2, 1, "", "topleft"], [9, 2, 1, "", "topright"], [9, 2, 1, "", "topt"], [9, 2, 1, "", "up"], [9, 2, 1, "", "vline"]], "pomdp_py.utils.plotting": [[9, 5, 1, "", "plot_circle"], [9, 5, 1, "", "plot_line"], [9, 5, 1, "", "plot_points"], [9, 5, 1, "", "plot_polygons"], [9, 5, 1, "", "save_plot"]], "pomdp_py.utils.templates": [[9, 1, 1, "", "DetObservationModel"], [9, 1, 1, "", "DetRewardModel"], [9, 1, 1, "", "DetTransitionModel"], [9, 1, 1, "", "SimpleAction"], [9, 1, 1, "", "SimpleObservation"], [9, 1, 1, "", "SimpleState"], [9, 1, 1, "", "TabularObservationModel"], [9, 1, 1, "", "TabularRewardModel"], [9, 1, 1, "", "TabularTransitionModel"], [9, 1, 1, "", "UniformPolicyModel"]], "pomdp_py.utils.templates.DetObservationModel": [[9, 3, 1, "", "probability"], [9, 3, 1, "", "sample"]], "pomdp_py.utils.templates.DetRewardModel": [[9, 3, 1, "", "argmax"], [9, 3, 1, "", "reward_func"], [9, 3, 1, "", "sample"]], "pomdp_py.utils.templates.DetTransitionModel": [[9, 3, 1, "", "probability"], [9, 3, 1, "", "sample"]], "pomdp_py.utils.templates.TabularObservationModel": [[9, 3, 1, "", "get_all_observations"], [9, 3, 1, "", "probability"], [9, 3, 1, "", "sample"]], "pomdp_py.utils.templates.TabularRewardModel": [[9, 3, 1, "", "sample"]], "pomdp_py.utils.templates.TabularTransitionModel": [[9, 3, 1, "", "get_all_states"], [9, 3, 1, "", "probability"], [9, 3, 1, "", "sample"]], "pomdp_py.utils.templates.UniformPolicyModel": [[9, 3, 1, "", "get_all_actions"], [9, 3, 1, "", "rollout"], [9, 3, 1, "", "sample"]], "pomdp_py.utils.test_utils": [[9, 5, 1, "", "make_tiger"], [9, 5, 1, "", "remove_files"]], "pomdp_py.utils.typ": [[9, 1, 1, "", "bcolors"], [9, 5, 1, "", "blue"], [9, 5, 1, "", "bold"], [9, 5, 1, "", "cyan"], [9, 5, 1, "", "error"], [9, 5, 1, "", "green"], [9, 5, 1, "", "info"], [9, 5, 1, "", "magenta"], [9, 5, 1, "", "note"], [9, 5, 1, "", "red"], [9, 5, 1, "", "success"], [9, 5, 1, "", "warning"], [9, 5, 1, "", "white"], [9, 5, 1, "", "yellow"]], "pomdp_py.utils.typ.bcolors": [[9, 2, 1, "", "BLUE"], [9, 2, 1, "", "BOLD"], [9, 2, 1, "", "CYAN"], [9, 2, 1, "", "ENDC"], [9, 2, 1, "", "GREEN"], [9, 2, 1, "", "MAGENTA"], [9, 2, 1, "", "RED"], [9, 2, 1, "", "WHITE"], [9, 2, 1, "", "YELLOW"], [9, 3, 1, "", "disable"], [9, 3, 1, "", "s"]], "pomdp_py.visual": [[12, 0, 0, "-", "search_tree"]], "pomdp_py.visual.search_tree": [[12, 5, 1, "", "visualize_pouct_search_tree"]]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:attribute", "3": "py:method", "4": "py:property", "5": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "attribute", "Python attribute"], "3": ["py", "method", "Python method"], "4": ["py", "property", "Python property"], "5": ["py", "function", "Python function"]}, "titleterms": {"pomdp_pi": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 18, 24, 58], "packag": [1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 12, 29, 30, 32, 34, 35, 37, 38, 39, 40, 41, 43, 44, 45, 46, 47, 49, 51, 52, 53, 54, 55, 57, 58], "algorithm": [2, 3, 4], "po_rollout": 2, "modul": [2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "po_uct": 2, "pomcp": 2, "value_iter": 2, "bsp": [2, 3], "blqr": [2, 3], "visual": [2, 4, 12, 34, 45, 53], "submodul": [3, 4, 9, 12, 31, 32, 33, 34, 35, 36, 38, 39, 41, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57], "content": [3, 4, 9, 12, 18, 25, 30, 31, 32, 33, 34, 35, 38, 39, 40, 41, 47, 48, 49, 51, 52, 53, 54, 55, 57], "framework": 5, "basic": 5, "oopomdp": 5, "planner": 5, "represent": [6, 7, 8], "belief": [7, 32, 43], "histogram": [7, 8], "particl": [7, 8], "distribut": 8, "gaussian": 8, "util": [9, 10, 11, 58], "subpackag": [9, 31, 40, 48, 50, 54, 56], "color": 9, "cython_util": 9, "cpython": [9, 48, 49, 56, 57], "37m": [9, 48, 49, 56, 57], "x86_64": [9, 48, 49, 56, 57], "linux": [9, 48, 49, 56, 57], "gnu": [9, 48, 49, 56, 57], "debug": [9, 10], "treedebugg": [9, 10], "math": 9, "misc": 9, "plot": 9, "templat": 9, "test_util": 9, "typ": 9, "interfac": [11, 58], "simple_rl": [11, 58], "search_tre": 12, "build": 13, "document": [13, 24], "doc": [13, 26], "pomdp_problem": [13, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57], "note": 13, "changelog": [13, 14], "design": 15, "principl": 15, "exampl": [16, 18], "tiger": [16, 20, 56, 57], "multi": [16, 19, 42], "object": [16, 19, 42], "search": [16, 19, 42], "mo": [16, 19, 42], "prefer": 17, "base": 17, "action": [17, 33, 38, 44, 52], "prior": 17, "us": [18, 23], "extern": 18, "solver": [18, 22], "tabl": [18, 25], "convert": 18, "agent": [18, 32, 43, 51], "pomdp": [18, 19, 20, 21, 22, 25, 27], "file": 18, "solv": [18, 20], "sarsop": 18, "policygraph": 18, "alphavectorpolici": 18, "problem": [19, 42, 50], "overview": [19, 24], "implement": 19, "thi": 19, "convent": 19, "try": 19, "defin": 20, "domain": [20, 21, 33, 38, 44, 52], "model": [20, 35, 40, 41, 46, 47, 54, 55], "instanti": 20, "instanc": 20, "summari": 20, "exist": [21, 22], "case": 23, "extens": 23, "get": 24, "start": 24, "further": 24, "citat": 24, "api": 24, "refer": 24, "tool": 24, "instal": 25, "pre": 25, "py": 25, "test": [25, 31], "thing": 25, "out": 25, "docker": 25, "imag": 25, "other": 27, "librari": 27, "lasertag": 30, "light": 31, "dark": 31, "light_dark": [31, 32, 33, 34, 35], "problem_discret": 31, "observ": [33, 38, 44, 52], "state": [33, 38, 44, 52], "env": [34, 39, 45, 53], "observation_model": [35, 46, 54], "transition_model": [35, 46, 54], "load": 36, "unload": 36, "load_unload": 36, "maze": [37, 38, 39, 40, 41], "compon": [41, 47, 55], "map": 41, "task": 42, "multi_object_search": [42, 43, 44, 45, 46, 47], "example_world": [42, 50], "policy_model": [46, 54], "reward_model": [46, 54], "grid_map": [47, 55], "sensor": 47, "rocksampl": [48, 49], "rocksample_problem": [48, 49], "cython": [48, 49, 56, 57], "38": [48, 49, 56, 57], "run_rocksampl": 49, "tag": [50, 51, 52, 53, 54, 55], "constant": 50, "experi": 50, "motion_polici": 55, "tiger_problem": [56, 57], "run_tig": 57, "integr": 58, "version": 14, "1": 14, "3": 14, "07": 14, "25": 14, "2023": 14, "2": 14, "04": 14, "03": 14, "2022": 14, "11": 14, "2021": 14, "0": 14, "09": 14, "30": 14, "4": 14, "6": 14, "cancel": 14, "5": 14, "05": 14, "06": 14, "02": 14, "01": 14, "22": 14, "17": 14, "12": 14, "23": 14, "2020": 14, "pull": 14, "request": 14, "08": 14, "16": 14}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinxcontrib.bibtex": 9, "sphinx.ext.viewcode": 1, "sphinx": 58}, "alltitles": {"pomdp_py": [[0, "pomdp-py"]], "pomdp_py package": [[1, "pomdp-py-package"]], "pomdp_py.algorithms.bsp.blqr module": [[3, "module-pomdp_py.algorithms.bsp.blqr"], [2, "module-pomdp_py.algorithms.bsp.blqr"]], "pomdp_py.algorithms.bsp package": [[3, "pomdp-py-algorithms-bsp-package"]], "Submodules": [[3, "submodules"], [12, "submodules"], [32, "submodules"], [33, "submodules"], [34, "submodules"], [35, "submodules"], [36, "submodules"], [38, "submodules"], [39, "submodules"], [47, "submodules"], [48, "submodules"], [50, "submodules"], [51, "submodules"], [52, "submodules"], [53, "submodules"], [54, "submodules"], [55, "submodules"], [9, "submodules"], [56, "submodules"], [4, "submodules"], [31, "submodules"], [41, "submodules"], [49, "submodules"], [57, "submodules"]], "Module contents": [[3, "module-pomdp_py.algorithms.bsp"], [12, "module-pomdp_py.visual"], [30, "module-pomdp_problems.lasertag"], [32, "module-pomdp_problems.light_dark.agent"], [33, "module-pomdp_problems.light_dark.domain"], [34, "module-pomdp_problems.light_dark.env"], [35, "module-pomdp_problems.light_dark.models"], [38, "module-pomdp_problems.maze.domain"], [39, "module-pomdp_problems.maze.env"], [40, "module-pomdp_problems.maze.models"], [47, "module-pomdp_problems.multi_object_search.models.components"], [48, "module-pomdp_problems.rocksample"], [51, "module-pomdp_problems.tag.agent"], [52, "module-pomdp_problems.tag.domain"], [53, "module-pomdp_problems.tag.env"], [54, "module-pomdp_problems.tag.models"], [55, "module-pomdp_problems.tag.models.components"], [9, "module-pomdp_py.utils"], [4, "module-contents"], [31, "module-pomdp_problems.light_dark"], [41, "module-pomdp_problems.maze.models.components"], [49, "module-pomdp_problems.rocksample.cythonize"], [57, "module-pomdp_problems.tiger.cythonize"]], "pomdp_py.framework package": [[5, "pomdp-py-framework-package"]], "pomdp_py.framework.basics module": [[5, "module-pomdp_py.framework.basics"]], "pomdp_py.framework.oopomdp module": [[5, "module-pomdp_py.framework.oopomdp"]], "pomdp_py.framework.planner module": [[5, "module-pomdp_py.framework.planner"]], "pomdp_py.representations package": [[6, "pomdp-py-representations-package"]], "pomdp_py.representations.belief package": [[7, "pomdp-py-representations-belief-package"]], "pomdp_py.representations.belief.histogram module": [[7, "module-pomdp_py.representations.belief.histogram"]], "pomdp_py.representations.belief.particles module": [[7, "module-pomdp_py.representations.belief.particles"]], "pomdp_py.representations.distribution package": [[8, "pomdp-py-representations-distribution-package"]], "pomdp_py.representations.distribution.histogram module": [[8, "module-pomdp_py.representations.distribution.histogram"]], "pomdp_py.representations.distribution.particles module": [[8, "module-pomdp_py.representations.distribution.particles"]], "pomdp_py.representations.distribution.gaussian module": [[8, "module-pomdp_py.representations.distribution.gaussian"]], "pomdp_py.utils.debugging module": [[10, "module-pomdp_py.utils.debugging"], [9, "module-pomdp_py.utils.debugging"]], "TreeDebugger": [[10, "treedebugger"], [9, "treedebugger"]], "pomdp_py.visual package": [[12, "pomdp-py-visual-package"]], "pomdp_py.visual.search_tree module": [[12, "module-pomdp_py.visual.search_tree"]], "Building Documentations": [[13, "building-documentations"]], "Building docs for pomdp_py": [[13, "building-docs-for-pomdp-py"]], "Building docs for pomdp_problems": [[13, "building-docs-for-pomdp-problems"]], "Note on Changelog": [[13, "note-on-changelog"]], "Design Principles": [[15, "design-principles"]], "Examples": [[16, "examples"]], "Tiger": [[16, "tiger"], [20, "tiger"], [56, "tiger"]], "Multi-Object Search (MOS)": [[16, "multi-object-search-mos"], [19, "multi-object-search-mos"]], "Preference-based Action Prior": [[17, "preference-based-action-prior"]], "Using External Solvers": [[18, "module-pomdp_py.utils.interfaces.solvers"]], "Table of Contents": [[18, "table-of-contents"], [25, "table-of-contents"]], "Converting a pomdp_py Agent to a POMDP File": [[18, "converting-a-pomdp-py-agent-to-a-pomdp-file"]], "Example": [[18, "example"], [18, "id2"], [18, "id4"]], "Using pomdp-solve": [[18, "using-pomdp-solve"]], "Using sarsop": [[18, "using-sarsop"]], "PolicyGraph and AlphaVectorPolicy": [[18, "policygraph-and-alphavectorpolicy"]], "Problem overview": [[19, "problem-overview"]], "Implementing this POMDP: Conventions": [[19, "implementing-this-pomdp-conventions"]], "Try it": [[19, "try-it"]], "Define the domain": [[20, "define-the-domain"]], "Define the models": [[20, "define-the-models"]], "Define the POMDP": [[20, "define-the-pomdp"]], "Instantiate the POMDP": [[20, "instantiate-the-pomdp"]], "Solve the POMDP instance": [[20, "solve-the-pomdp-instance"]], "Summary": [[20, "summary"]], "Existing POMDP Domains": [[21, "existing-pomdp-domains"]], "Existing POMDP Solvers": [[22, "existing-pomdp-solvers"]], "Use Case Extensions": [[23, "use-case-extensions"]], "docs": [[26, "docs"]], "Other POMDP Libraries": [[27, "other-pomdp-libraries"]], "pomdp_problems": [[28, "pomdp-problems"]], "pomdp_problems package": [[29, "pomdp-problems-package"]], "pomdp_problems.lasertag package": [[30, "pomdp-problems-lasertag-package"]], "pomdp_problems.light_dark.agent package": [[32, "pomdp-problems-light-dark-agent-package"]], "pomdp_problems.light_dark.agent.belief module": [[32, "module-pomdp_problems.light_dark.agent.belief"]], "pomdp_problems.light_dark.domain.action module": [[33, "module-pomdp_problems.light_dark.domain.action"]], "pomdp_problems.light_dark.domain.observation module": [[33, "module-pomdp_problems.light_dark.domain.observation"]], "pomdp_problems.light_dark.domain.state module": [[33, "module-pomdp_problems.light_dark.domain.state"]], "pomdp_problems.light_dark.env package": [[34, "pomdp-problems-light-dark-env-package"]], "pomdp_problems.light_dark.env.env module": [[34, "module-pomdp_problems.light_dark.env.env"]], "pomdp_problems.light_dark.env.visual module": [[34, "module-pomdp_problems.light_dark.env.visual"]], "pomdp_problems.light_dark.models package": [[35, "pomdp-problems-light-dark-models-package"]], "pomdp_problems.light_dark.models.observation_model module": [[35, "module-pomdp_problems.light_dark.models.observation_model"]], "pomdp_problems.light_dark.models.transition_model module": [[35, "module-pomdp_problems.light_dark.models.transition_model"]], "Load/Unload": [[36, "load-unload"]], "pomdp_problems.load_unload.load_unload module": [[36, "module-pomdp_problems.load_unload.load_unload"]], "pomdp_problems.maze package": [[37, "module-pomdp_problems.maze"]], "Maze": [[37, "maze"]], "pomdp_problems.maze.domain package": [[38, "pomdp-problems-maze-domain-package"]], "pomdp_problems.maze.domain.action module": [[38, "module-pomdp_problems.maze.domain.action"]], "pomdp_problems.maze.domain.observation module": [[38, "module-pomdp_problems.maze.domain.observation"]], "pomdp_problems.maze.domain.state module": [[38, "module-pomdp_problems.maze.domain.state"]], "pomdp_problems.maze.env package": [[39, "pomdp-problems-maze-env-package"]], "pomdp_problems.maze.env.env module": [[39, "module-pomdp_problems.maze.env.env"]], "pomdp_problems.maze.models package": [[40, "pomdp-problems-maze-models-package"]], "Subpackages": [[40, "subpackages"], [48, "subpackages"], [50, "subpackages"], [54, "subpackages"], [9, "subpackages"], [56, "subpackages"], [31, "subpackages"]], "Multi-Object Search (MOS) Task": [[42, "multi-object-search-mos-task"]], "pomdp_problems.multi_object_search.problem module": [[42, "module-pomdp_problems.multi_object_search.problem"]], "pomdp_problems.multi_object_search.example_worlds module": [[42, "module-pomdp_problems.multi_object_search.example_worlds"]], "pomdp_problems.multi_object_search.agent package": [[43, "pomdp-problems-multi-object-search-agent-package"]], "pomdp_problems.multi_object_search.agent.agent module": [[43, "module-pomdp_problems.multi_object_search.agent.agent"]], "pomdp_problems.multi_object_search.agent.belief module": [[43, "module-pomdp_problems.multi_object_search.agent.belief"]], "pomdp_problems.multi_object_search.domain package": [[44, "pomdp-problems-multi-object-search-domain-package"]], "pomdp_problems.multi_object_search.domain.action module": [[44, "module-pomdp_problems.multi_object_search.domain.action"]], "pomdp_problems.multi_object_search.domain.observation module": [[44, "module-pomdp_problems.multi_object_search.domain.observation"]], "pomdp_problems.multi_object_search.domain.state module": [[44, "module-pomdp_problems.multi_object_search.domain.state"]], "pomdp_problems.multi_object_search.env package": [[45, "pomdp-problems-multi-object-search-env-package"]], "pomdp_problems.multi_object_search.env.env module": [[45, "module-pomdp_problems.multi_object_search.env.env"]], "pomdp_problems.multi_object_search.env.visual module": [[45, "module-pomdp_problems.multi_object_search.env.visual"]], "pomdp_problems.multi_object_search.models package": [[46, "pomdp-problems-multi-object-search-models-package"]], "pomdp_problems.multi_object_search.models.observation_model module": [[46, "module-pomdp_problems.multi_object_search.models.observation_model"]], "pomdp_problems.multi_object_search.models.policy_model module": [[46, "module-pomdp_problems.multi_object_search.models.policy_model"]], "pomdp_problems.multi_object_search.models.reward_model module": [[46, "module-pomdp_problems.multi_object_search.models.reward_model"]], "pomdp_problems.multi_object_search.models.transition_model module": [[46, "module-pomdp_problems.multi_object_search.models.transition_model"]], "pomdp_problems.multi_object_search.models.components package": [[47, "pomdp-problems-multi-object-search-models-components-package"]], "pomdp_problems.multi_object_search.models.components.grid_map module": [[47, "module-pomdp_problems.multi_object_search.models.components.grid_map"]], "pomdp_problems.multi_object_search.models.components.sensor module": [[47, "module-pomdp_problems.multi_object_search.models.components.sensor"]], "RockSample": [[48, "rocksample"]], "pomdp_problems.rocksample.rocksample_problem module": [[48, "module-pomdp_problems.rocksample.rocksample_problem"], [48, "id1"]], "pomdp_problems.rocksample.cythonize.cpython-37m-x86_64-linux-gnu module": [[48, "pomdp-problems-rocksample-cythonize-cpython-37m-x86-64-linux-gnu-module"]], "pomdp_problems.rocksample.cythonize.cpython-38-x86_64-linux-gnu module": [[48, "pomdp-problems-rocksample-cythonize-cpython-38-x86-64-linux-gnu-module"]], "Tag": [[50, "tag"]], "pomdp_problems.tag.constants module": [[50, "module-pomdp_problems.tag.constants"]], "pomdp_problems.tag.example_worlds module": [[50, "module-pomdp_problems.tag.example_worlds"]], "pomdp_problems.tag.experiment module": [[50, "module-pomdp_problems.tag.experiment"]], "pomdp_problems.tag.problem module": [[50, "module-pomdp_problems.tag.problem"]], "pomdp_problems.tag.agent package": [[51, "pomdp-problems-tag-agent-package"]], "pomdp_problems.tag.agent.agent module": [[51, "module-pomdp_problems.tag.agent.agent"]], "pomdp_problems.tag.domain package": [[52, "pomdp-problems-tag-domain-package"]], "pomdp_problems.tag.domain.action module": [[52, "module-pomdp_problems.tag.domain.action"]], "pomdp_problems.tag.domain.observation module": [[52, "module-pomdp_problems.tag.domain.observation"]], "pomdp_problems.tag.domain.state module": [[52, "module-pomdp_problems.tag.domain.state"]], "pomdp_problems.tag.env package": [[53, "pomdp-problems-tag-env-package"]], "pomdp_problems.tag.env.env module": [[53, "module-pomdp_problems.tag.env.env"]], "pomdp_problems.tag.env.visual module": [[53, "module-pomdp_problems.tag.env.visual"]], "pomdp_problems.tag.models package": [[54, "pomdp-problems-tag-models-package"]], "pomdp_problems.tag.models.observation_model module": [[54, "module-pomdp_problems.tag.models.observation_model"]], "pomdp_problems.tag.models.policy_model module": [[54, "module-pomdp_problems.tag.models.policy_model"]], "pomdp_problems.tag.models.reward_model module": [[54, "module-pomdp_problems.tag.models.reward_model"]], "pomdp_problems.tag.models.transition_model module": [[54, "module-pomdp_problems.tag.models.transition_model"]], "pomdp_problems.tag.models.components package": [[55, "pomdp-problems-tag-models-components-package"]], "pomdp_problems.tag.models.components.grid_map module": [[55, "module-pomdp_problems.tag.models.components.grid_map"]], "pomdp_problems.tag.models.components.motion_policy module": [[55, "module-pomdp_problems.tag.models.components.motion_policy"]], "pomdp_py Documentation": [[24, "pomdp-py-documentation"]], "Overview": [[24, "overview"]], "Getting Started": [[24, "getting-started"]], "Further": [[24, "further"]], "Citation": [[24, "citation"]], "API References": [[24, "api-references"], [24, null]], "Tools": [[24, "tools"]], "pomdp_py.utils package": [[9, "pomdp-py-utils-package"]], "pomdp_py.utils.colors module": [[9, "module-pomdp_py.utils.colors"]], "pomdp_py.utils.cython_utils.cpython-37m-x86_64-linux-gnu module": [[9, "pomdp-py-utils-cython-utils-cpython-37m-x86-64-linux-gnu-module"]], "pomdp_py.utils.cython_utils module": [[9, "module-pomdp_py.utils.cython_utils"]], "pomdp_py.utils.math module": [[9, "module-pomdp_py.utils.math"]], "pomdp_py.utils.misc module": [[9, "module-pomdp_py.utils.misc"]], "pomdp_py.utils.plotting module": [[9, "module-pomdp_py.utils.plotting"]], "pomdp_py.utils.templates module": [[9, "module-pomdp_py.utils.templates"]], "pomdp_py.utils.test_utils module": [[9, "module-pomdp_py.utils.test_utils"]], "pomdp_py.utils.typ module": [[9, "module-pomdp_py.utils.typ"]], "pomdp_problems.tiger.cythonize.cpython-37m-x86_64-linux-gnu module": [[56, "pomdp-problems-tiger-cythonize-cpython-37m-x86-64-linux-gnu-module"]], "pomdp_problems.tiger.cythonize.cpython-38-x86_64-linux-gnu module": [[56, "pomdp-problems-tiger-cythonize-cpython-38-x86-64-linux-gnu-module"]], "pomdp_problems.tiger.tiger_problem module": [[56, "module-pomdp_problems.tiger.tiger_problem"]], "Changelog": [[14, "changelog"]], "Version 1.3.3 (07/25/2023)": [[14, "version-1-3-3-07-25-2023"]], "Version 1.3.2 (04/03/2022)": [[14, "version-1-3-2-04-03-2022"]], "Version 1.3.1 (11/03/2021)": [[14, "version-1-3-1-11-03-2021"]], "Version 1.3.0.1 (09/30/2021)": [[14, "version-1-3-0-1-09-30-2021"]], "Version 1.2.4.6 (canceled)": [[14, "version-1-2-4-6-canceled"]], "Version 1.2.4.5 (07/05/2021)": [[14, "version-1-2-4-5-07-05-2021"]], "Version 1.2.4.1 (06/02/2021)": [[14, "version-1-2-4-1-06-02-2021"]], "Version 1.2.4 (06/01/2021)": [[14, "version-1-2-4-06-01-2021"]], "Version 1.2.3 (03/22/2021)": [[14, "version-1-2-3-03-22-2021"]], "Version 1.2.2.1 (01/25/2021)": [[14, "version-1-2-2-1-01-25-2021"]], "Version 1.2.2 (01/17/2021)": [[14, "version-1-2-2-01-17-2021"]], "Version 1.2.1 (12/23/2020)": [[14, "version-1-2-1-12-23-2020"]], "Pull Request #3 (08/01/2020)": [[14, "pull-request-3-08-01-2020"]], "Pull Request #1 (06/02/2020)": [[14, "pull-request-1-06-02-2020"]], "Version 1.0 - 1.2 (02/08/2020 - 02/16/2020)": [[14, "version-1-0-1-2-02-08-2020-02-16-2020"]], "Version 0.0": [[14, "version-0-0"]], "pomdp_py.algorithms package": [[2, "pomdp-py-algorithms-package"]], "pomdp_py.algorithms.po_rollout module": [[2, "module-pomdp_py.algorithms.po_rollout"]], "pomdp_py.algorithms.po_uct module": [[2, "module-pomdp_py.algorithms.po_uct"]], "pomdp_py.algorithms.pomcp module": [[2, "module-pomdp_py.algorithms.pomcp"]], "pomdp_py.algorithms.value_iteration module": [[2, "module-pomdp_py.algorithms.value_iteration"]], "pomdp_py.algorithms.visual.visual module": [[2, "pomdp-py-algorithms-visual-visual-module"], [4, "pomdp-py-algorithms-visual-visual-module"]], "pomdp_py.algorithms.visual package": [[4, "pomdp-py-algorithms-visual-package"]], "pomdp_py.utils.interfaces package": [[11, "pomdp-py-utils-interfaces-package"], [58, "pomdp-py-utils-interfaces-package"]], "pomdp_py.utils.interfaces.simple_rl module": [[11, "pomdp-py-utils-interfaces-simple-rl-module"], [58, "pomdp-py-utils-interfaces-simple-rl-module"]], "Installation": [[25, "installation"]], "Pre-installation": [[25, "pre-installation"]], "Install pomdp-py": [[25, "install-pomdp-py"]], "Test things out": [[25, "test-things-out"]], "Docker image": [[25, "docker-image"]], "Light-Dark": [[31, "light-dark"]], "pomdp_problems.light_dark.problem_discrete module": [[31, "module-pomdp_problems.light_dark.problem_discrete"]], "pomdp_problems.light_dark.test module": [[31, "pomdp-problems-light-dark-test-module"]], "pomdp_problems.maze.models.components package": [[41, "pomdp-problems-maze-models-components-package"]], "pomdp_problems.maze.models.components.map module": [[41, "pomdp-problems-maze-models-components-map-module"]], "pomdp_problems.rocksample.cythonize package": [[49, "pomdp-problems-rocksample-cythonize-package"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.cpython-37m-x86_64-linux-gnu module": [[49, "pomdp-problems-rocksample-cythonize-rocksample-problem-cpython-37m-x86-64-linux-gnu-module"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.cpython-38-x86_64-linux-gnu module": [[49, "pomdp-problems-rocksample-cythonize-rocksample-problem-cpython-38-x86-64-linux-gnu-module"]], "pomdp_problems.rocksample.cythonize.rocksample_problem module": [[49, "module-pomdp_problems.rocksample.cythonize.rocksample_problem"]], "pomdp_problems.rocksample.cythonize.run_rocksample module": [[49, "pomdp-problems-rocksample-cythonize-run-rocksample-module"]], "pomdp_problems.tiger.cythonize package": [[57, "pomdp-problems-tiger-cythonize-package"]], "pomdp_problems.tiger.cythonize.run_tiger module": [[57, "pomdp-problems-tiger-cythonize-run-tiger-module"]], "pomdp_problems.tiger.cythonize.tiger_problem.cpython-37m-x86_64-linux-gnu module": [[57, "pomdp-problems-tiger-cythonize-tiger-problem-cpython-37m-x86-64-linux-gnu-module"]], "pomdp_problems.tiger.cythonize.tiger_problem.cpython-38-x86_64-linux-gnu module": [[57, "pomdp-problems-tiger-cythonize-tiger-problem-cpython-38-x86-64-linux-gnu-module"]], "pomdp_problems.tiger.cythonize.tiger_problem module": [[57, "module-pomdp_problems.tiger.cythonize.tiger_problem"]], "Integration with simple_rl": [[58, "integration-with-simple-rl"]]}, "indexentries": {"actionprior (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.ActionPrior"]], "blqr (class in pomdp_py.algorithms.bsp.blqr)": [[2, "pomdp_py.algorithms.bsp.blqr.BLQR"]], "pomcp (class in pomdp_py.algorithms.pomcp)": [[2, "pomdp_py.algorithms.pomcp.POMCP"]], "porollout (class in pomdp_py.algorithms.po_rollout)": [[2, "pomdp_py.algorithms.po_rollout.PORollout"]], "pouct (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.POUCT"]], "qnode (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.QNode"]], "randomrollout (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.RandomRollout"]], "rolloutpolicy (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.RolloutPolicy"]], "rootvnode (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.RootVNode"]], "rootvnodeparticles (class in pomdp_py.algorithms.pomcp)": [[2, "pomdp_py.algorithms.pomcp.RootVNodeParticles"]], "treenode (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.TreeNode"]], "vnode (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.VNode"]], "vnodeparticles (class in pomdp_py.algorithms.pomcp)": [[2, "pomdp_py.algorithms.pomcp.VNodeParticles"]], "valueiteration (class in pomdp_py.algorithms.value_iteration)": [[2, "pomdp_py.algorithms.value_iteration.ValueIteration"]], "argmax() (pomdp_py.algorithms.po_uct.vnode method)": [[2, "pomdp_py.algorithms.po_uct.VNode.argmax"]], "belief (pomdp_py.algorithms.pomcp.rootvnodeparticles attribute)": [[2, "pomdp_py.algorithms.pomcp.RootVNodeParticles.belief"]], "belief (pomdp_py.algorithms.pomcp.vnodeparticles attribute)": [[2, "pomdp_py.algorithms.pomcp.VNodeParticles.belief"]], "children (pomdp_py.algorithms.po_uct.treenode attribute)": [[2, "pomdp_py.algorithms.po_uct.TreeNode.children"]], "clear_agent() (pomdp_py.algorithms.po_rollout.porollout method)": [[2, "pomdp_py.algorithms.po_rollout.PORollout.clear_agent"]], "clear_agent() (pomdp_py.algorithms.po_uct.pouct method)": [[2, "pomdp_py.algorithms.po_uct.POUCT.clear_agent"]], "create_plan() (pomdp_py.algorithms.bsp.blqr.blqr method)": [[2, "pomdp_py.algorithms.bsp.blqr.BLQR.create_plan"]], "ekf_update_mlo() (pomdp_py.algorithms.bsp.blqr.blqr method)": [[2, "pomdp_py.algorithms.bsp.blqr.BLQR.ekf_update_mlo"]], "from_vnode() (pomdp_py.algorithms.po_uct.rootvnode class method)": [[2, "pomdp_py.algorithms.po_uct.RootVNode.from_vnode"]], "from_vnode() (pomdp_py.algorithms.pomcp.rootvnodeparticles class method)": [[2, "pomdp_py.algorithms.pomcp.RootVNodeParticles.from_vnode"]], "get_preferred_actions() (pomdp_py.algorithms.po_uct.actionprior method)": [[2, "pomdp_py.algorithms.po_uct.ActionPrior.get_preferred_actions"]], "history (pomdp_py.algorithms.po_uct.rootvnode attribute)": [[2, "pomdp_py.algorithms.po_uct.RootVNode.history"]], "integrate_belief_segment() (pomdp_py.algorithms.bsp.blqr.blqr method)": [[2, "pomdp_py.algorithms.bsp.blqr.BLQR.integrate_belief_segment"]], "interpret_sqp_plan() (pomdp_py.algorithms.bsp.blqr.blqr method)": [[2, "pomdp_py.algorithms.bsp.blqr.BLQR.interpret_sqp_plan"]], "last_best_reward (pomdp_py.algorithms.po_rollout.porollout attribute)": [[2, "pomdp_py.algorithms.po_rollout.PORollout.last_best_reward"]], "last_num_sims (pomdp_py.algorithms.po_uct.pouct attribute)": [[2, "pomdp_py.algorithms.po_uct.POUCT.last_num_sims"]], "last_planning_time (pomdp_py.algorithms.po_uct.pouct attribute)": [[2, "pomdp_py.algorithms.po_uct.POUCT.last_planning_time"]], "module": [[2, "module-pomdp_py.algorithms.bsp.blqr"], [2, "module-pomdp_py.algorithms.po_rollout"], [2, "module-pomdp_py.algorithms.po_uct"], [2, "module-pomdp_py.algorithms.pomcp"], [2, "module-pomdp_py.algorithms.value_iteration"], [9, "module-pomdp_py.utils"], [9, "module-pomdp_py.utils.colors"], [9, "module-pomdp_py.utils.cython_utils"], [9, "module-pomdp_py.utils.debugging"], [9, "module-pomdp_py.utils.math"], [9, "module-pomdp_py.utils.misc"], [9, "module-pomdp_py.utils.plotting"], [9, "module-pomdp_py.utils.templates"], [9, "module-pomdp_py.utils.test_utils"], [9, "module-pomdp_py.utils.typ"], [31, "module-pomdp_problems.light_dark"], [31, "module-pomdp_problems.light_dark.problem_discrete"], [40, "module-pomdp_problems.maze.models"], [41, "module-pomdp_problems.maze.models.components"], [48, "module-0"], [48, "module-pomdp_problems.rocksample"], [48, "module-pomdp_problems.rocksample.rocksample_problem"], [49, "module-pomdp_problems.rocksample.cythonize"], [49, "module-pomdp_problems.rocksample.cythonize.rocksample_problem"], [56, "module-pomdp_problems.tiger.tiger_problem"], [57, "module-pomdp_problems.tiger.cythonize"], [57, "module-pomdp_problems.tiger.cythonize.tiger_problem"]], "num_visits (pomdp_py.algorithms.po_uct.treenode attribute)": [[2, "pomdp_py.algorithms.po_uct.TreeNode.num_visits"]], "plan() (pomdp_py.algorithms.po_rollout.porollout method)": [[2, "pomdp_py.algorithms.po_rollout.PORollout.plan"]], "plan() (pomdp_py.algorithms.po_uct.pouct method)": [[2, "pomdp_py.algorithms.po_uct.POUCT.plan"]], "plan() (pomdp_py.algorithms.pomcp.pomcp method)": [[2, "pomdp_py.algorithms.pomcp.POMCP.plan"]], "plan() (pomdp_py.algorithms.value_iteration.valueiteration method)": [[2, "pomdp_py.algorithms.value_iteration.ValueIteration.plan"]], "pomdp_py.algorithms.bsp.blqr": [[2, "module-pomdp_py.algorithms.bsp.blqr"]], "pomdp_py.algorithms.po_rollout": [[2, "module-pomdp_py.algorithms.po_rollout"]], "pomdp_py.algorithms.po_uct": [[2, "module-pomdp_py.algorithms.po_uct"]], "pomdp_py.algorithms.pomcp": [[2, "module-pomdp_py.algorithms.pomcp"]], "pomdp_py.algorithms.value_iteration": [[2, "module-pomdp_py.algorithms.value_iteration"]], "print_children_value() (pomdp_py.algorithms.po_uct.vnode method)": [[2, "pomdp_py.algorithms.po_uct.VNode.print_children_value"]], "rollout() (pomdp_py.algorithms.po_uct.randomrollout method)": [[2, "pomdp_py.algorithms.po_uct.RandomRollout.rollout"]], "rollout() (pomdp_py.algorithms.po_uct.rolloutpolicy method)": [[2, "pomdp_py.algorithms.po_uct.RolloutPolicy.rollout"]], "segmented_cost_function() (pomdp_py.algorithms.bsp.blqr.blqr method)": [[2, "pomdp_py.algorithms.bsp.blqr.BLQR.segmented_cost_function"]], "set_rollout_policy() (pomdp_py.algorithms.po_rollout.porollout method)": [[2, "pomdp_py.algorithms.po_rollout.PORollout.set_rollout_policy"]], "set_rollout_policy() (pomdp_py.algorithms.po_uct.pouct method)": [[2, "pomdp_py.algorithms.po_uct.POUCT.set_rollout_policy"]], "update() (pomdp_py.algorithms.po_rollout.porollout method)": [[2, "pomdp_py.algorithms.po_rollout.PORollout.update"]], "update() (pomdp_py.algorithms.po_uct.pouct method)": [[2, "pomdp_py.algorithms.po_uct.POUCT.update"]], "update() (pomdp_py.algorithms.pomcp.pomcp method)": [[2, "pomdp_py.algorithms.pomcp.POMCP.update"]], "update_agent_belief (pomdp_py.algorithms.po_rollout.porollout attribute)": [[2, "pomdp_py.algorithms.po_rollout.PORollout.update_agent_belief"]], "update_agent_belief (pomdp_py.algorithms.pomcp.pomcp attribute)": [[2, "pomdp_py.algorithms.pomcp.POMCP.update_agent_belief"]], "updates_agent_belief (pomdp_py.algorithms.po_uct.pouct attribute)": [[2, "pomdp_py.algorithms.po_uct.POUCT.updates_agent_belief"]], "value (pomdp_py.algorithms.po_uct.treenode attribute)": [[2, "pomdp_py.algorithms.po_uct.TreeNode.value"]], "value (pomdp_py.algorithms.po_uct.vnode attribute)": [[2, "pomdp_py.algorithms.po_uct.VNode.value"]], "blue (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.BLUE"]], "bold (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.BOLD"]], "cyan (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.CYAN"]], "detobservationmodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.DetObservationModel"]], "detrewardmodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.DetRewardModel"]], "dettransitionmodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.DetTransitionModel"]], "endc (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.ENDC"]], "green (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.GREEN"]], "magenta (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.MAGENTA"]], "red (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.RED"]], "r_between() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.R_between"]], "r_x() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.R_x"]], "r_y() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.R_y"]], "r_z() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.R_z"]], "subscript (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.SUBSCRIPT"]], "simpleaction (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.SimpleAction"]], "simpleobservation (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.SimpleObservation"]], "simplestate (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.SimpleState"]], "t() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.T"]], "tabularobservationmodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.TabularObservationModel"]], "tabularrewardmodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.TabularRewardModel"]], "tabulartransitionmodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.TabularTransitionModel"]], "treedebugger (class in pomdp_py.utils.debugging)": [[9, "pomdp_py.utils.debugging.TreeDebugger"]], "uniformpolicymodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.UniformPolicyModel"]], "white (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.WHITE"]], "yellow (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.YELLOW"]], "approx_equal() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.approx_equal"]], "argmax() (pomdp_py.utils.templates.detrewardmodel method)": [[9, "pomdp_py.utils.templates.DetRewardModel.argmax"]], "b (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.b"]], "back() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.back"]], "bcolors (class in pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.bcolors"]], "bestseq (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.bestseq"]], "bestseqd() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.bestseqd"]], "blue() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.blue"]], "bold() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.bold"]], "bottomleft (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.bottomleft"]], "bottomright (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.bottomright"]], "bottomt (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.bottomt"]], "c (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.c"]], "clear (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.clear"]], "cyan() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.cyan"]], "d (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.d"]], "depth (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.depth"]], "det_dict_hash() (in module pomdp_py.utils.cython_utils)": [[9, "pomdp_py.utils.cython_utils.det_dict_hash"]], "disable() (pomdp_py.utils.typ.bcolors static method)": [[9, "pomdp_py.utils.typ.bcolors.disable"]], "down (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.down"]], "error() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.error"]], "euclidean_dist() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.euclidean_dist"]], "get_all_actions() (pomdp_py.utils.templates.uniformpolicymodel method)": [[9, "pomdp_py.utils.templates.UniformPolicyModel.get_all_actions"]], "get_all_observations() (pomdp_py.utils.templates.tabularobservationmodel method)": [[9, "pomdp_py.utils.templates.TabularObservationModel.get_all_observations"]], "get_all_states() (pomdp_py.utils.templates.tabulartransitionmodel method)": [[9, "pomdp_py.utils.templates.TabularTransitionModel.get_all_states"]], "green() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.green"]], "hex_to_rgb() (in module pomdp_py.utils.colors)": [[9, "pomdp_py.utils.colors.hex_to_rgb"]], "hline (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.hline"]], "info() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.info"]], "interpret_color() (in module pomdp_py.utils.debugging)": [[9, "pomdp_py.utils.debugging.interpret_color"]], "intersect (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.intersect"]], "inverse_color_hex() (in module pomdp_py.utils.colors)": [[9, "pomdp_py.utils.colors.inverse_color_hex"]], "inverse_color_rgb() (in module pomdp_py.utils.colors)": [[9, "pomdp_py.utils.colors.inverse_color_rgb"]], "json_safe() (in module pomdp_py.utils.misc)": [[9, "pomdp_py.utils.misc.json_safe"]], "l() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.l"]], "layer() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.layer"]], "leaf (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.leaf"]], "left (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.left"]], "leftt (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.leftt"]], "lighter() (in module pomdp_py.utils.colors)": [[9, "pomdp_py.utils.colors.lighter"]], "longbottomleft (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.longbottomleft"]], "longbottomright (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.longbottomright"]], "longleft (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.longleft"]], "longright (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.longright"]], "longtopleft (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.longtopleft"]], "longtopright (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.longtopright"]], "magenta() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.magenta"]], "make_tiger() (in module pomdp_py.utils.test_utils)": [[9, "pomdp_py.utils.test_utils.make_tiger"]], "mark() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.mark"]], "mark_path() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.mark_path"]], "mark_sequence() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.mark_sequence"]], "markp() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.markp"]], "mbp (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.mbp"]], "nl (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.nl"]], "nn (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.nn"]], "note() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.note"]], "nq (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.nq"]], "num_layers (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.num_layers"]], "num_nodes() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.num_nodes"]], "nv (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.nv"]], "p() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.p"]], "path() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.path"]], "path_to() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.path_to"]], "plot_circle() (in module pomdp_py.utils.plotting)": [[9, "pomdp_py.utils.plotting.plot_circle"]], "plot_line() (in module pomdp_py.utils.plotting)": [[9, "pomdp_py.utils.plotting.plot_line"]], "plot_points() (in module pomdp_py.utils.plotting)": [[9, "pomdp_py.utils.plotting.plot_points"]], "plot_polygons() (in module pomdp_py.utils.plotting)": [[9, "pomdp_py.utils.plotting.plot_polygons"]], "pm (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.pm"]], "pomdp_py.utils": [[9, "module-pomdp_py.utils"]], "pomdp_py.utils.colors": [[9, "module-pomdp_py.utils.colors"]], "pomdp_py.utils.cython_utils": [[9, "module-pomdp_py.utils.cython_utils"]], "pomdp_py.utils.debugging": [[9, "module-pomdp_py.utils.debugging"]], "pomdp_py.utils.math": [[9, "module-pomdp_py.utils.math"]], "pomdp_py.utils.misc": [[9, "module-pomdp_py.utils.misc"]], "pomdp_py.utils.plotting": [[9, "module-pomdp_py.utils.plotting"]], "pomdp_py.utils.templates": [[9, "module-pomdp_py.utils.templates"]], "pomdp_py.utils.test_utils": [[9, "module-pomdp_py.utils.test_utils"]], "pomdp_py.utils.typ": [[9, "module-pomdp_py.utils.typ"]], "pp (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.pp"]], "preferred_actions() (pomdp_py.utils.debugging.treedebugger static method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.preferred_actions"]], "probability() (pomdp_py.utils.templates.detobservationmodel method)": [[9, "pomdp_py.utils.templates.DetObservationModel.probability"]], "probability() (pomdp_py.utils.templates.dettransitionmodel method)": [[9, "pomdp_py.utils.templates.DetTransitionModel.probability"]], "probability() (pomdp_py.utils.templates.tabularobservationmodel method)": [[9, "pomdp_py.utils.templates.TabularObservationModel.probability"]], "probability() (pomdp_py.utils.templates.tabulartransitionmodel method)": [[9, "pomdp_py.utils.templates.TabularTransitionModel.probability"]], "proj() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.proj"]], "r (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.r"]], "random_unique_color() (in module pomdp_py.utils.colors)": [[9, "pomdp_py.utils.colors.random_unique_color"]], "red() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.red"]], "remap() (in module pomdp_py.utils.misc)": [[9, "pomdp_py.utils.misc.remap"]], "remove_files() (in module pomdp_py.utils.test_utils)": [[9, "pomdp_py.utils.test_utils.remove_files"]], "reward_func() (pomdp_py.utils.templates.detrewardmodel method)": [[9, "pomdp_py.utils.templates.DetRewardModel.reward_func"]], "rgb_to_hex() (in module pomdp_py.utils.colors)": [[9, "pomdp_py.utils.colors.rgb_to_hex"]], "right (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.right"]], "rightt (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.rightt"]], "rollout() (pomdp_py.utils.templates.uniformpolicymodel method)": [[9, "pomdp_py.utils.templates.UniformPolicyModel.rollout"]], "root (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.root"]], "s() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.s"]], "s() (pomdp_py.utils.typ.bcolors static method)": [[9, "pomdp_py.utils.typ.bcolors.s"]], "safe_slice() (in module pomdp_py.utils.misc)": [[9, "pomdp_py.utils.misc.safe_slice"]], "sample() (pomdp_py.utils.templates.detobservationmodel method)": [[9, "pomdp_py.utils.templates.DetObservationModel.sample"]], "sample() (pomdp_py.utils.templates.detrewardmodel method)": [[9, "pomdp_py.utils.templates.DetRewardModel.sample"]], "sample() (pomdp_py.utils.templates.dettransitionmodel method)": [[9, "pomdp_py.utils.templates.DetTransitionModel.sample"]], "sample() (pomdp_py.utils.templates.tabularobservationmodel method)": [[9, "pomdp_py.utils.templates.TabularObservationModel.sample"]], "sample() (pomdp_py.utils.templates.tabularrewardmodel method)": [[9, "pomdp_py.utils.templates.TabularRewardModel.sample"]], "sample() (pomdp_py.utils.templates.tabulartransitionmodel method)": [[9, "pomdp_py.utils.templates.TabularTransitionModel.sample"]], "sample() (pomdp_py.utils.templates.uniformpolicymodel method)": [[9, "pomdp_py.utils.templates.UniformPolicyModel.sample"]], "save_plot() (in module pomdp_py.utils.plotting)": [[9, "pomdp_py.utils.plotting.save_plot"]], "shadebar (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.shadebar"]], "similar() (in module pomdp_py.utils.misc)": [[9, "pomdp_py.utils.misc.similar"]], "single_node_str() (pomdp_py.utils.debugging.treedebugger static method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.single_node_str"]], "sorted_by_str() (in module pomdp_py.utils.debugging)": [[9, "pomdp_py.utils.debugging.sorted_by_str"]], "special_char (class in pomdp_py.utils.misc)": [[9, "pomdp_py.utils.misc.special_char"]], "step() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.step"]], "success() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.success"]], "to_radians() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.to_radians"]], "topleft (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.topleft"]], "topright (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.topright"]], "topt (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.topt"]], "tree_stats() (pomdp_py.utils.debugging.treedebugger static method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.tree_stats"]], "up (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.up"]], "vec() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.vec"]], "vline (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.vline"]], "warning() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.warning"]], "white() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.white"]], "yellow() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.yellow"]], "discretelightdark (class in pomdp_problems.light_dark.problem_discrete)": [[31, "pomdp_problems.light_dark.problem_discrete.DiscreteLightDark"]], "pomdp_problems.light_dark": [[31, "module-pomdp_problems.light_dark"]], "pomdp_problems.light_dark.problem_discrete": [[31, "module-pomdp_problems.light_dark.problem_discrete"]], "pomdp_problems.maze.models": [[40, "module-pomdp_problems.maze.models"]], "pomdp_problems.maze.models.components": [[41, "module-pomdp_problems.maze.models.components"]], "action (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id8"], [48, "pomdp_problems.rocksample.rocksample_problem.Action"]], "bad (pomdp_problems.rocksample.rocksample_problem.rocktype attribute)": [[48, "id4"], [48, "pomdp_problems.rocksample.rocksample_problem.RockType.BAD"]], "checkaction (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id15"], [48, "pomdp_problems.rocksample.rocksample_problem.CheckAction"]], "east (pomdp_problems.rocksample.rocksample_problem.moveaction attribute)": [[48, "id10"], [48, "pomdp_problems.rocksample.rocksample_problem.MoveAction.EAST"]], "good (pomdp_problems.rocksample.rocksample_problem.rocktype attribute)": [[48, "id3"], [48, "pomdp_problems.rocksample.rocksample_problem.RockType.GOOD"]], "moveaction (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id9"], [48, "pomdp_problems.rocksample.rocksample_problem.MoveAction"]], "north (pomdp_problems.rocksample.rocksample_problem.moveaction attribute)": [[48, "id12"], [48, "pomdp_problems.rocksample.rocksample_problem.MoveAction.NORTH"]], "observation (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id16"], [48, "pomdp_problems.rocksample.rocksample_problem.Observation"]], "rsobservationmodel (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id21"], [48, "pomdp_problems.rocksample.rocksample_problem.RSObservationModel"]], "rspolicymodel (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id29"], [48, "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel"]], "rsrewardmodel (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id25"], [48, "pomdp_problems.rocksample.rocksample_problem.RSRewardModel"]], "rstransitionmodel (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id17"], [48, "pomdp_problems.rocksample.rocksample_problem.RSTransitionModel"]], "rocksampleproblem (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id35"], [48, "pomdp_problems.rocksample.rocksample_problem.RockSampleProblem"]], "rocktype (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id2"], [48, "pomdp_problems.rocksample.rocksample_problem.RockType"]], "south (pomdp_problems.rocksample.rocksample_problem.moveaction attribute)": [[48, "id13"], [48, "pomdp_problems.rocksample.rocksample_problem.MoveAction.SOUTH"]], "sampleaction (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id14"], [48, "pomdp_problems.rocksample.rocksample_problem.SampleAction"]], "state (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id7"], [48, "pomdp_problems.rocksample.rocksample_problem.State"]], "west (pomdp_problems.rocksample.rocksample_problem.moveaction attribute)": [[48, "id11"], [48, "pomdp_problems.rocksample.rocksample_problem.MoveAction.WEST"]], "argmax() (pomdp_problems.rocksample.rocksample_problem.rsobservationmodel method)": [[48, "id24"], [48, "pomdp_problems.rocksample.rocksample_problem.RSObservationModel.argmax"]], "argmax() (pomdp_problems.rocksample.rocksample_problem.rspolicymodel method)": [[48, "id32"], [48, "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel.argmax"]], "argmax() (pomdp_problems.rocksample.rocksample_problem.rsrewardmodel method)": [[48, "id27"], [48, "pomdp_problems.rocksample.rocksample_problem.RSRewardModel.argmax"]], "argmax() (pomdp_problems.rocksample.rocksample_problem.rstransitionmodel method)": [[48, "id20"], [48, "pomdp_problems.rocksample.rocksample_problem.RSTransitionModel.argmax"]], "euclidean_dist() (in module pomdp_problems.rocksample.rocksample_problem)": [[48, "id0"], [48, "pomdp_problems.rocksample.rocksample_problem.euclidean_dist"]], "generate_instance() (pomdp_problems.rocksample.rocksample_problem.rocksampleproblem static method)": [[48, "id38"], [48, "pomdp_problems.rocksample.rocksample_problem.RockSampleProblem.generate_instance"]], "get_all_actions() (pomdp_problems.rocksample.rocksample_problem.rspolicymodel method)": [[48, "id33"], [48, "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel.get_all_actions"]], "in_exit_area() (pomdp_problems.rocksample.rocksample_problem.rocksampleproblem method)": [[48, "id37"], [48, "pomdp_problems.rocksample.rocksample_problem.RockSampleProblem.in_exit_area"]], "init_particles_belief() (in module pomdp_problems.rocksample.rocksample_problem)": [[48, "id41"], [48, "pomdp_problems.rocksample.rocksample_problem.init_particles_belief"]], "invert() (pomdp_problems.rocksample.rocksample_problem.rocktype static method)": [[48, "id5"], [48, "pomdp_problems.rocksample.rocksample_problem.RockType.invert"]], "main() (in module pomdp_problems.rocksample.rocksample_problem)": [[48, "id42"], [48, "pomdp_problems.rocksample.rocksample_problem.main"]], "pomdp_problems.rocksample": [[48, "module-pomdp_problems.rocksample"]], "pomdp_problems.rocksample.rocksample_problem": [[48, "module-0"], [48, "module-pomdp_problems.rocksample.rocksample_problem"]], "print_state() (pomdp_problems.rocksample.rocksample_problem.rocksampleproblem method)": [[48, "id39"], [48, "pomdp_problems.rocksample.rocksample_problem.RockSampleProblem.print_state"]], "probability() (pomdp_problems.rocksample.rocksample_problem.rsobservationmodel method)": [[48, "id22"], [48, "pomdp_problems.rocksample.rocksample_problem.RSObservationModel.probability"]], "probability() (pomdp_problems.rocksample.rocksample_problem.rspolicymodel method)": [[48, "id31"], [48, "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel.probability"]], "probability() (pomdp_problems.rocksample.rocksample_problem.rsrewardmodel method)": [[48, "id28"], [48, "pomdp_problems.rocksample.rocksample_problem.RSRewardModel.probability"]], "probability() (pomdp_problems.rocksample.rocksample_problem.rstransitionmodel method)": [[48, "id18"], [48, "pomdp_problems.rocksample.rocksample_problem.RSTransitionModel.probability"]], "random() (pomdp_problems.rocksample.rocksample_problem.rocktype static method)": [[48, "id6"], [48, "pomdp_problems.rocksample.rocksample_problem.RockType.random"]], "random_free_location() (pomdp_problems.rocksample.rocksample_problem.rocksampleproblem static method)": [[48, "id36"], [48, "pomdp_problems.rocksample.rocksample_problem.RockSampleProblem.random_free_location"]], "rollout() (pomdp_problems.rocksample.rocksample_problem.rspolicymodel method)": [[48, "id34"], [48, "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel.rollout"]], "sample() (pomdp_problems.rocksample.rocksample_problem.rsobservationmodel method)": [[48, "id23"], [48, "pomdp_problems.rocksample.rocksample_problem.RSObservationModel.sample"]], "sample() (pomdp_problems.rocksample.rocksample_problem.rspolicymodel method)": [[48, "id30"], [48, "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel.sample"]], "sample() (pomdp_problems.rocksample.rocksample_problem.rsrewardmodel method)": [[48, "id26"], [48, "pomdp_problems.rocksample.rocksample_problem.RSRewardModel.sample"]], "sample() (pomdp_problems.rocksample.rocksample_problem.rstransitionmodel method)": [[48, "id19"], [48, "pomdp_problems.rocksample.rocksample_problem.RSTransitionModel.sample"]], "test_planner() (in module pomdp_problems.rocksample.rocksample_problem)": [[48, "id40"], [48, "pomdp_problems.rocksample.rocksample_problem.test_planner"]], "bad (pomdp_problems.rocksample.cythonize.rocksample_problem.rocktype attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockType.BAD"]], "checkaction (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.CheckAction"]], "east (pomdp_problems.rocksample.cythonize.rocksample_problem.moveaction attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction.EAST"]], "good (pomdp_problems.rocksample.cythonize.rocksample_problem.rocktype attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockType.GOOD"]], "moveaction (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction"]], "north (pomdp_problems.rocksample.cythonize.rocksample_problem.moveaction attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction.NORTH"]], "rsaction (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSAction"]], "rsobservation (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservation"]], "rsobservationmodel (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservationModel"]], "rspolicymodel (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel"]], "rsrewardmodel (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSRewardModel"]], "rsstate (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSState"]], "rstransitionmodel (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSTransitionModel"]], "rocksampleproblem (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockSampleProblem"]], "rocktype (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockType"]], "south (pomdp_problems.rocksample.cythonize.rocksample_problem.moveaction attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction.SOUTH"]], "sampleaction (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.SampleAction"]], "west (pomdp_problems.rocksample.cythonize.rocksample_problem.moveaction attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction.WEST"]], "argmax() (pomdp_problems.rocksample.cythonize.rocksample_problem.rsobservationmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservationModel.argmax"]], "argmax() (pomdp_problems.rocksample.cythonize.rocksample_problem.rspolicymodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel.argmax"]], "argmax() (pomdp_problems.rocksample.cythonize.rocksample_problem.rsrewardmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSRewardModel.argmax"]], "argmax() (pomdp_problems.rocksample.cythonize.rocksample_problem.rstransitionmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSTransitionModel.argmax"]], "euclidean_dist() (in module pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.euclidean_dist"]], "generate_instance() (pomdp_problems.rocksample.cythonize.rocksample_problem.rocksampleproblem static method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockSampleProblem.generate_instance"]], "get_all_actions() (pomdp_problems.rocksample.cythonize.rocksample_problem.rspolicymodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel.get_all_actions"]], "in_exit_area() (pomdp_problems.rocksample.cythonize.rocksample_problem.rocksampleproblem method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockSampleProblem.in_exit_area"]], "init_particles_belief() (in module pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.init_particles_belief"]], "invert() (pomdp_problems.rocksample.cythonize.rocksample_problem.rocktype static method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockType.invert"]], "main() (in module pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.main"]], "motion (pomdp_problems.rocksample.cythonize.rocksample_problem.moveaction attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction.motion"]], "pomdp_problems.rocksample.cythonize": [[49, "module-pomdp_problems.rocksample.cythonize"]], "pomdp_problems.rocksample.cythonize.rocksample_problem": [[49, "module-pomdp_problems.rocksample.cythonize.rocksample_problem"]], "position (pomdp_problems.rocksample.cythonize.rocksample_problem.rsstate attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSState.position"]], "print_state() (pomdp_problems.rocksample.cythonize.rocksample_problem.rocksampleproblem method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockSampleProblem.print_state"]], "probability() (pomdp_problems.rocksample.cythonize.rocksample_problem.rsobservationmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservationModel.probability"]], "probability() (pomdp_problems.rocksample.cythonize.rocksample_problem.rspolicymodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel.probability"]], "probability() (pomdp_problems.rocksample.cythonize.rocksample_problem.rsrewardmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSRewardModel.probability"]], "probability() (pomdp_problems.rocksample.cythonize.rocksample_problem.rstransitionmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSTransitionModel.probability"]], "quality (pomdp_problems.rocksample.cythonize.rocksample_problem.rsobservation attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservation.quality"]], "random() (pomdp_problems.rocksample.cythonize.rocksample_problem.rocktype static method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockType.random"]], "random_free_location() (pomdp_problems.rocksample.cythonize.rocksample_problem.rocksampleproblem static method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockSampleProblem.random_free_location"]], "rock_id (pomdp_problems.rocksample.cythonize.rocksample_problem.checkaction attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.CheckAction.rock_id"]], "rocktypes (pomdp_problems.rocksample.cythonize.rocksample_problem.rsstate attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSState.rocktypes"]], "rollout() (pomdp_problems.rocksample.cythonize.rocksample_problem.rspolicymodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel.rollout"]], "sample() (pomdp_problems.rocksample.cythonize.rocksample_problem.rsobservationmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservationModel.sample"]], "sample() (pomdp_problems.rocksample.cythonize.rocksample_problem.rspolicymodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel.sample"]], "sample() (pomdp_problems.rocksample.cythonize.rocksample_problem.rsrewardmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSRewardModel.sample"]], "sample() (pomdp_problems.rocksample.cythonize.rocksample_problem.rstransitionmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSTransitionModel.sample"]], "terminal (pomdp_problems.rocksample.cythonize.rocksample_problem.rsstate attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSState.terminal"]], "test_planner() (in module pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.test_planner"]], "actions (pomdp_problems.tiger.tiger_problem.policymodel attribute)": [[56, "pomdp_problems.tiger.tiger_problem.PolicyModel.ACTIONS"]], "observationmodel (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.ObservationModel"]], "policymodel (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.PolicyModel"]], "rewardmodel (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.RewardModel"]], "tigeraction (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.TigerAction"]], "tigerobservation (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.TigerObservation"]], "tigerproblem (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.TigerProblem"]], "tigerstate (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.TigerState"]], "transitionmodel (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.TransitionModel"]], "create() (pomdp_problems.tiger.tiger_problem.tigerproblem static method)": [[56, "pomdp_problems.tiger.tiger_problem.TigerProblem.create"]], "get_all_actions() (pomdp_problems.tiger.tiger_problem.policymodel method)": [[56, "pomdp_problems.tiger.tiger_problem.PolicyModel.get_all_actions"]], "get_all_observations() (pomdp_problems.tiger.tiger_problem.observationmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.ObservationModel.get_all_observations"]], "get_all_states() (pomdp_problems.tiger.tiger_problem.transitionmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.TransitionModel.get_all_states"]], "main() (in module pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.main"]], "other() (pomdp_problems.tiger.tiger_problem.tigerstate method)": [[56, "pomdp_problems.tiger.tiger_problem.TigerState.other"]], "pomdp_problems.tiger.tiger_problem": [[56, "module-pomdp_problems.tiger.tiger_problem"]], "probability() (pomdp_problems.tiger.tiger_problem.observationmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.ObservationModel.probability"]], "probability() (pomdp_problems.tiger.tiger_problem.transitionmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.TransitionModel.probability"]], "rollout() (pomdp_problems.tiger.tiger_problem.policymodel method)": [[56, "pomdp_problems.tiger.tiger_problem.PolicyModel.rollout"]], "sample() (pomdp_problems.tiger.tiger_problem.observationmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.ObservationModel.sample"]], "sample() (pomdp_problems.tiger.tiger_problem.policymodel method)": [[56, "pomdp_problems.tiger.tiger_problem.PolicyModel.sample"]], "sample() (pomdp_problems.tiger.tiger_problem.rewardmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.RewardModel.sample"]], "sample() (pomdp_problems.tiger.tiger_problem.transitionmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.TransitionModel.sample"]], "test_planner() (in module pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.test_planner"]], "actions (pomdp_problems.tiger.cythonize.tiger_problem.tigerproblem attribute)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerProblem.ACTIONS"]], "observations (pomdp_problems.tiger.cythonize.tiger_problem.tigerproblem attribute)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerProblem.OBSERVATIONS"]], "states (pomdp_problems.tiger.cythonize.tiger_problem.tigerproblem attribute)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerProblem.STATES"]], "tigeraction (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerAction"]], "tigerobservation (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservation"]], "tigerobservationmodel (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel"]], "tigerpolicymodel (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerPolicyModel"]], "tigerproblem (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerProblem"]], "tigerrewardmodel (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerRewardModel"]], "tigerstate (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerState"]], "tigertransitionmodel (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel"]], "argmax() (pomdp_problems.tiger.cythonize.tiger_problem.tigerobservationmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel.argmax"]], "argmax() (pomdp_problems.tiger.cythonize.tiger_problem.tigerpolicymodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerPolicyModel.argmax"]], "argmax() (pomdp_problems.tiger.cythonize.tiger_problem.tigerrewardmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerRewardModel.argmax"]], "argmax() (pomdp_problems.tiger.cythonize.tiger_problem.tigertransitionmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel.argmax"]], "build_actions() (in module pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.build_actions"]], "build_observations() (in module pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.build_observations"]], "build_setting() (in module pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.build_setting"]], "build_states() (in module pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.build_states"]], "get_all_actions() (pomdp_problems.tiger.cythonize.tiger_problem.tigerpolicymodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerPolicyModel.get_all_actions"]], "get_all_observations() (pomdp_problems.tiger.cythonize.tiger_problem.tigerobservationmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel.get_all_observations"]], "get_all_states() (pomdp_problems.tiger.cythonize.tiger_problem.tigertransitionmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel.get_all_states"]], "get_distribution() (pomdp_problems.tiger.cythonize.tiger_problem.tigerobservationmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel.get_distribution"]], "get_distribution() (pomdp_problems.tiger.cythonize.tiger_problem.tigerrewardmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerRewardModel.get_distribution"]], "get_distribution() (pomdp_problems.tiger.cythonize.tiger_problem.tigertransitionmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel.get_distribution"]], "main() (in module pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.main"]], "name (pomdp_problems.tiger.cythonize.tiger_problem.tigerobservation attribute)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservation.name"]], "name (pomdp_problems.tiger.cythonize.tiger_problem.tigerstate attribute)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerState.name"]], "pomdp_problems.tiger.cythonize": [[57, "module-pomdp_problems.tiger.cythonize"]], "pomdp_problems.tiger.cythonize.tiger_problem": [[57, "module-pomdp_problems.tiger.cythonize.tiger_problem"]], "probability() (pomdp_problems.tiger.cythonize.tiger_problem.tigerobservationmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel.probability"]], "probability() (pomdp_problems.tiger.cythonize.tiger_problem.tigerpolicymodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerPolicyModel.probability"]], "probability() (pomdp_problems.tiger.cythonize.tiger_problem.tigerrewardmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerRewardModel.probability"]], "probability() (pomdp_problems.tiger.cythonize.tiger_problem.tigertransitionmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel.probability"]], "sample() (pomdp_problems.tiger.cythonize.tiger_problem.tigerobservationmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel.sample"]], "sample() (pomdp_problems.tiger.cythonize.tiger_problem.tigerpolicymodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerPolicyModel.sample"]], "sample() (pomdp_problems.tiger.cythonize.tiger_problem.tigerrewardmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerRewardModel.sample"]], "sample() (pomdp_problems.tiger.cythonize.tiger_problem.tigertransitionmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel.sample"]], "test_planner() (in module pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.test_planner"]]}}) \ No newline at end of file +Search.setIndex({"docnames": ["api/modules", "api/pomdp_py", "api/pomdp_py.algorithms", "api/pomdp_py.algorithms.bsp", "api/pomdp_py.algorithms.visual", "api/pomdp_py.framework", "api/pomdp_py.representations", "api/pomdp_py.representations.belief", "api/pomdp_py.representations.distribution", "api/pomdp_py.utils", "api/pomdp_py.utils.debugging", "api/pomdp_py.utils.interfaces", "api/pomdp_py.visual", "building_docs", "changelog", "design_principles", "examples", "examples.action_prior", "examples.external_solvers", "examples.mos", "examples.tiger", "existing_domains", "existing_solvers", "extensions", "index", "installation", "modules", "other_libraries", "problems/modules", "problems/pomdp_problems", "problems/pomdp_problems.lasertag", "problems/pomdp_problems.light_dark", "problems/pomdp_problems.light_dark.agent", "problems/pomdp_problems.light_dark.domain", "problems/pomdp_problems.light_dark.env", "problems/pomdp_problems.light_dark.models", "problems/pomdp_problems.load_unload", "problems/pomdp_problems.maze", "problems/pomdp_problems.maze.domain", "problems/pomdp_problems.maze.env", "problems/pomdp_problems.maze.models", "problems/pomdp_problems.maze.models.components", "problems/pomdp_problems.multi_object_search", "problems/pomdp_problems.multi_object_search.agent", "problems/pomdp_problems.multi_object_search.domain", "problems/pomdp_problems.multi_object_search.env", "problems/pomdp_problems.multi_object_search.models", "problems/pomdp_problems.multi_object_search.models.components", "problems/pomdp_problems.rocksample", "problems/pomdp_problems.rocksample.cythonize", "problems/pomdp_problems.tag", "problems/pomdp_problems.tag.agent", "problems/pomdp_problems.tag.domain", "problems/pomdp_problems.tag.env", "problems/pomdp_problems.tag.models", "problems/pomdp_problems.tag.models.components", "problems/pomdp_problems.tiger", "problems/pomdp_problems.tiger.cythonize", "simple_rl_integration"], "filenames": ["api/modules.rst", "api/pomdp_py.rst", "api/pomdp_py.algorithms.rst", "api/pomdp_py.algorithms.bsp.rst", "api/pomdp_py.algorithms.visual.rst", "api/pomdp_py.framework.rst", "api/pomdp_py.representations.rst", "api/pomdp_py.representations.belief.rst", "api/pomdp_py.representations.distribution.rst", "api/pomdp_py.utils.rst", "api/pomdp_py.utils.debugging.rst", "api/pomdp_py.utils.interfaces.rst", "api/pomdp_py.visual.rst", "building_docs.rst", "changelog.rst", "design_principles.rst", "examples.rst", "examples.action_prior.rst", "examples.external_solvers.rst", "examples.mos.rst", "examples.tiger.rst", "existing_domains.rst", "existing_solvers.rst", "extensions.rst", "index.rst", "installation.rst", "modules.rst", "other_libraries.rst", "problems/modules.rst", "problems/pomdp_problems.rst", "problems/pomdp_problems.lasertag.rst", "problems/pomdp_problems.light_dark.rst", "problems/pomdp_problems.light_dark.agent.rst", "problems/pomdp_problems.light_dark.domain.rst", "problems/pomdp_problems.light_dark.env.rst", "problems/pomdp_problems.light_dark.models.rst", "problems/pomdp_problems.load_unload.rst", "problems/pomdp_problems.maze.rst", "problems/pomdp_problems.maze.domain.rst", "problems/pomdp_problems.maze.env.rst", "problems/pomdp_problems.maze.models.rst", "problems/pomdp_problems.maze.models.components.rst", "problems/pomdp_problems.multi_object_search.rst", "problems/pomdp_problems.multi_object_search.agent.rst", "problems/pomdp_problems.multi_object_search.domain.rst", "problems/pomdp_problems.multi_object_search.env.rst", "problems/pomdp_problems.multi_object_search.models.rst", "problems/pomdp_problems.multi_object_search.models.components.rst", "problems/pomdp_problems.rocksample.rst", "problems/pomdp_problems.rocksample.cythonize.rst", "problems/pomdp_problems.tag.rst", "problems/pomdp_problems.tag.agent.rst", "problems/pomdp_problems.tag.domain.rst", "problems/pomdp_problems.tag.env.rst", "problems/pomdp_problems.tag.models.rst", "problems/pomdp_problems.tag.models.components.rst", "problems/pomdp_problems.tiger.rst", "problems/pomdp_problems.tiger.cythonize.rst", "simple_rl_integration.rst"], "titles": ["pomdp_py", "pomdp_py package", "pomdp_py.algorithms package", "pomdp_py.algorithms.bsp package", "pomdp_py.algorithms.visual package", "pomdp_py.framework package", "pomdp_py.representations package", "pomdp_py.representations.belief package", "pomdp_py.representations.distribution package", "pomdp_py.utils package", "pomdp_py.utils.debugging module", "pomdp_py.utils.interfaces package", "pomdp_py.visual package", "Building Documentations", "Changelog", "Design Principles", "Examples", "Preference-based Action Prior", "Using External Solvers", "Multi-Object Search (MOS)", "Tiger", "Existing POMDP Domains", "Existing POMDP Solvers", "Use Case Extensions", "pomdp_py Documentation", "Installation", "docs", "Other POMDP Libraries", "pomdp_problems", "pomdp_problems package", "pomdp_problems.lasertag package", "Light-Dark", "pomdp_problems.light_dark.agent package", "Submodules", "pomdp_problems.light_dark.env package", "pomdp_problems.light_dark.models package", "Load/Unload", "pomdp_problems.maze package", "pomdp_problems.maze.domain package", "pomdp_problems.maze.env package", "pomdp_problems.maze.models package", "pomdp_problems.maze.models.components package", "Multi-Object Search (MOS) Task", "pomdp_problems.multi_object_search.agent package", "pomdp_problems.multi_object_search.domain package", "pomdp_problems.multi_object_search.env package", "pomdp_problems.multi_object_search.models package", "pomdp_problems.multi_object_search.models.components package", "RockSample", "pomdp_problems.rocksample.cythonize package", "Tag", "pomdp_problems.tag.agent package", "pomdp_problems.tag.domain package", "pomdp_problems.tag.env package", "pomdp_problems.tag.models package", "pomdp_problems.tag.models.components package", "Tiger", "pomdp_problems.tiger.cythonize package", "Integration with simple_rl"], "terms": {"packag": [0, 13, 19, 21, 24, 25, 28, 31, 42, 48, 50, 56], "algorithm": [0, 1, 5, 14, 18, 23, 24, 27, 31, 50], "po_rollout": [0, 1], "modul": [0, 1, 6, 13, 14, 19, 20, 24, 28, 29], "porollout": [0, 1, 2], "po_uct": [0, 1], "actionprior": [0, 1, 2, 14, 17, 20], "pouct": [0, 1, 2, 9, 10, 14, 17, 19, 20, 22, 23, 42, 50], "qnode": [0, 1, 2, 9, 10], "randomrollout": [0, 1, 2, 36, 57], "rolloutpolici": [0, 1, 2, 9, 17, 20, 46, 48, 49, 54, 56], "rootvnod": [0, 1, 2], "treenod": [0, 1, 2], "vnode": [0, 1, 2, 9, 10, 14], "pomcp": [0, 1, 7, 9, 10, 14, 17, 20, 22, 23, 25, 27, 42], "rootvnodeparticl": [0, 1, 2], "vnodeparticl": [0, 1, 2], "value_iter": [0, 1], "valueiter": [0, 1, 2, 14, 20, 22], "bsp": [0, 1], "blqr": [0, 1, 14, 31], "visual": [0, 1, 19, 25, 31, 42, 50], "framework": [0, 1, 14, 15, 19, 20, 24, 36, 57], "basic": [0, 1, 2, 7, 15, 18, 20, 22, 48, 49], "action": [0, 1, 2, 5, 7, 9, 10, 12, 14, 15, 18, 19, 20, 22, 25, 28, 31, 35, 36, 42, 45, 46, 47, 48, 49, 50, 53, 54, 55, 56, 57], "agent": [0, 1, 2, 5, 7, 9, 10, 15, 19, 20, 21, 22, 23, 24, 25, 28, 31, 36, 37, 38, 42, 46, 47, 48, 49, 50, 52, 56, 57], "blackboxmodel": [0, 1, 5, 7, 14, 20], "distribut": [0, 1, 2, 5, 6, 7, 9, 15, 17, 20, 35, 36, 43, 46, 48, 49, 54, 56, 57], "environ": [0, 1, 5, 14, 15, 19, 20, 34, 39, 42, 45, 46, 53, 56, 57], "generativedistribut": [0, 1, 5, 8, 43, 55], "observ": [0, 1, 2, 3, 5, 7, 9, 10, 12, 14, 15, 18, 19, 20, 22, 24, 25, 28, 31, 34, 35, 36, 37, 42, 45, 46, 47, 48, 49, 50, 53, 54, 56, 57], "observationmodel": [0, 1, 5, 7, 9, 15, 20, 23, 28, 31, 35, 36, 46, 48, 49, 54, 56, 57], "option": [0, 1, 2, 5, 9, 10, 14, 18, 20, 44, 46, 47, 48, 49, 56, 57], "pomdp": [0, 1, 2, 5, 9, 10, 13, 14, 15, 16, 17, 23, 24, 31, 36, 37, 42, 44, 46, 48, 49, 50, 52, 53, 54, 56, 57], "policymodel": [0, 1, 2, 5, 14, 17, 20, 23, 28, 42, 46, 56], "rewardmodel": [0, 1, 5, 9, 14, 15, 20, 28, 36, 46, 48, 49, 54, 56, 57], "state": [0, 1, 2, 3, 5, 7, 8, 9, 14, 15, 17, 18, 19, 20, 22, 25, 27, 28, 31, 35, 36, 37, 42, 43, 45, 46, 48, 49, 50, 54, 56, 57], "transitionmodel": [0, 1, 5, 7, 9, 15, 20, 23, 28, 31, 35, 36, 46, 48, 49, 54, 56, 57], "sample_explict_model": [0, 1, 5], "sample_generative_model": [0, 1, 5], "oopomdp": [0, 1, 14, 19, 23, 42], "oobelief": [0, 1, 5, 14, 43, 45, 53], "ooobserv": [0, 1, 5, 44], "ooobservationmodel": [0, 1, 5, 46], "oostat": [0, 1, 5, 14, 44], "ootransitionmodel": [0, 1, 5, 46], "objectst": [0, 1, 5, 42, 44], "planner": [0, 1, 2, 3, 18, 20, 36, 42, 48, 49, 56, 57], "represent": [0, 1, 2, 5, 14, 24, 43, 45], "belief": [0, 1, 2, 3, 5, 6, 8, 14, 18, 19, 20, 25, 31, 33, 34, 35, 36, 42, 45, 48, 49, 51, 53, 56], "histogram": [0, 1, 6, 14, 18, 20, 42, 43, 57], "particl": [0, 1, 2, 6, 14, 25, 43], "gaussian": [0, 1, 2, 3, 6, 35], "util": [0, 1, 12, 14, 18, 24], "subpackag": [0, 1, 28, 29], "interfac": [0, 1, 5, 9, 14, 15, 18, 19, 20, 21, 22, 23, 24, 27], "submodul": [0, 1, 28, 29, 40], "color": [0, 1, 10, 45, 53], "lighter": [0, 1, 9], "rgb_to_hex": [0, 1, 9], "hex_to_rgb": [0, 1, 9], "inverse_color_rgb": [0, 1, 9], "inverse_color_hex": [0, 1, 9], "random_unique_color": [0, 1, 9], "cython_util": [0, 1], "cpython": [0, 1, 28, 29], "37m": [0, 1, 28, 29], "x86_64": [0, 1, 28, 29], "linux": [0, 1, 25, 28, 29], "gnu": [0, 1, 28, 29], "det_dict_hash": [0, 1, 9], "debug": [0, 1, 12, 14, 24], "treedebugg": [0, 1, 12, 14, 56], "sorted_by_str": [0, 1, 9, 10], "interpret_color": [0, 1, 9, 10], "math": [0, 1, 2, 5, 14, 35], "vec": [0, 1, 9], "proj": [0, 1, 9], "r_x": [0, 1, 9], "r_y": [0, 1, 9], "r_z": [0, 1, 9], "t": [0, 1, 2, 3, 5, 7, 8, 9, 15, 18, 20, 22, 27, 42, 43, 45, 56, 57], "to_radian": [0, 1, 9], "r_between": [0, 1, 9], "approx_equ": [0, 1, 9], "euclidean_dist": [0, 1, 9, 28, 47, 48, 49], "misc": [0, 1], "remap": [0, 1, 9], "json_saf": [0, 1, 9], "safe_slic": [0, 1, 9], "similar": [0, 1, 9, 18, 20], "special_char": [0, 1, 9], "plot": [0, 1, 25, 31, 34], "plot_point": [0, 1, 9], "save_plot": [0, 1, 9], "plot_polygon": [0, 1, 9], "plot_lin": [0, 1, 9], "plot_circl": [0, 1, 9], "templat": [0, 1, 14], "simplest": [0, 1, 9], "simpleact": [0, 1, 9], "simpleobserv": [0, 1, 9], "dettransitionmodel": [0, 1, 9], "detobservationmodel": [0, 1, 9], "detrewardmodel": [0, 1, 9], "uniformpolicymodel": [0, 1, 9], "tabulartransitionmodel": [0, 1, 9, 14], "tabularobservationmodel": [0, 1, 9, 14], "tabularrewardmodel": [0, 1, 9, 14], "test_util": [0, 1], "remove_fil": [0, 1, 9], "make_tig": [0, 1, 9], "typ": [0, 1], "bcolor": [0, 1, 9], "info": [0, 1, 9], "note": [0, 1, 2, 5, 7, 8, 9, 10, 17, 18, 20, 24, 25, 31, 42, 46, 56, 57], "error": [0, 1, 9, 14], "warn": [0, 1, 2, 9, 10, 18], "success": [0, 1, 2, 9], "bold": [0, 1, 9], "cyan": [0, 1, 9], "magenta": [0, 1, 9], "blue": [0, 1, 9, 10], "green": [0, 1, 9, 25], "yellow": [0, 1, 9], "red": [0, 1, 9, 19], "white": [0, 1, 9], "content": [0, 1, 13, 24, 28, 29, 50, 56], "clear_ag": [1, 2], "last_best_reward": [1, 2], "plan": [1, 2, 3, 5, 9, 10, 14, 17, 18, 20, 23, 24, 27, 31, 33, 34, 35, 42, 46, 47, 50, 56], "set_rollout_polici": [1, 2], "updat": [1, 2, 3, 5, 7, 9, 10, 14, 18, 19, 20, 42, 45, 50, 53], "update_agent_belief": [1, 2, 5], "get_preferred_act": [1, 2, 17], "last_num_sim": [1, 2, 20], "last_planning_tim": [1, 2], "updates_agent_belief": [1, 2, 5], "rollout": [1, 2, 9, 14, 17, 20, 42, 46, 48, 49, 50, 54, 56], "from_vnod": [1, 2], "histori": [1, 2, 5, 9, 10, 17, 20, 43, 46, 48, 49, 51, 54, 56], "children": [1, 2, 9, 10, 14], "num_visit": [1, 2], "valu": [1, 2, 5, 6, 8, 9, 10, 14, 17, 18, 20, 25, 27, 48, 49, 50, 55, 56], "argmax": [1, 2, 5, 9, 14, 20, 31, 35, 36, 42, 46, 48, 49, 50, 54, 56, 57], "print_children_valu": [1, 2], "ekf_update_mlo": [1, 2, 3], "integrate_belief_seg": [1, 2, 3], "segmented_cost_funct": [1, 2, 3], "create_plan": [1, 2, 3], "interpret_sqp_plan": [1, 2, 3], "add_attr": [1, 5], "all_act": [1, 5], "all_observ": [1, 5], "all_stat": [1, 5], "init_belief": [1, 5, 9, 20, 36, 48, 51, 56, 57], "sample_belief": [1, 5], "set_belief": [1, 5, 18, 20], "update_histori": [1, 5, 20], "sampl": [1, 2, 5, 8, 9, 14, 17, 18, 20, 25, 31, 35, 36, 42, 43, 46, 48, 49, 50, 54, 56, 57], "__getitem__": [1, 5, 6, 8, 9, 10], "__setitem__": [1, 5, 6, 8], "apply_transit": [1, 5], "blackbox_model": [1, 5, 7], "cur_stat": [1, 5], "provide_observ": [1, 5], "reward_model": [1, 5, 19, 20, 34, 42, 50], "state_transit": [1, 5, 18, 20, 42, 45], "transition_model": [1, 5, 7, 18, 19, 20, 31, 42, 50], "get_histogram": [1, 5, 6, 8], "mpe": [1, 5, 6, 8, 14, 43, 50, 54, 55], "get_all_observ": [1, 5, 9, 20, 56, 57], "get_distribut": [1, 5, 56, 57], "probabl": [1, 5, 8, 9, 14, 15, 18, 20, 22, 31, 35, 36, 37, 42, 43, 46, 48, 49, 50, 54, 55, 56, 57], "initi": [1, 5, 14, 17, 18, 19, 20, 31, 43, 45, 48, 49, 51, 56], "polici": [1, 2, 5, 9, 14, 17, 18, 20, 36, 37, 46, 48, 49, 54, 56, 57], "termin": [1, 2, 5, 9, 10, 18, 20, 42, 48, 49], "get_all_act": [1, 5, 9, 17, 20, 36, 42, 46, 48, 49, 50, 54, 56, 57], "get_all_st": [1, 5, 9, 20, 56, 57], "b": [1, 2, 3, 5, 7, 9, 10, 18], "object_belief": [1, 5, 43], "random": [1, 2, 5, 6, 8, 9, 14, 17, 20, 43, 46, 48, 49, 50, 54, 55], "set_object_belief": [1, 5], "factor": [1, 5, 18, 42, 44], "merg": [1, 5, 42, 44], "observation_model": [1, 5, 7, 18, 19, 20, 31, 42, 50, 53], "copi": [1, 5, 25], "get_object_attribut": [1, 5], "get_object_class": [1, 5], "get_object_st": [1, 5], "": [1, 2, 3, 5, 7, 9, 10, 13, 14, 15, 18, 20, 22, 24, 31, 35, 36, 37, 42, 44, 45, 46, 47, 48, 49, 52, 54, 56, 57], "set_object_st": [1, 5], "situat": [1, 5, 19], "abstraction_over_histogram": [1, 6, 7], "update_histogram_belief": [1, 6, 7, 18, 20], "abstraction_over_particl": [1, 6, 7], "particle_reinvigor": [1, 6, 7], "update_particles_belief": [1, 6, 7], "is_norm": [1, 6, 8], "add": [1, 2, 6, 8, 14, 43], "from_histogram": [1, 6, 8], "get_abstract": [1, 6, 8], "weightedparticl": [1, 6, 8, 14], "condens": [1, 6, 8], "weight": [1, 2, 6, 8, 9], "cov": [1, 6, 8], "covari": [1, 2, 3, 6, 8], "mean": [1, 2, 6, 7, 8, 18, 35, 45, 47, 50], "sigma": [1, 6, 8, 42, 43, 46], "simple_rl": [1, 9, 24, 27], "num_nod": [1, 9, 10], "depth": [1, 2, 9, 10, 12], "d": [1, 2, 3, 9, 10, 20, 24], "num_lay": [1, 9, 10], "nl": [1, 9, 10], "nn": [1, 9, 10], "nq": [1, 9, 10], "nv": [1, 9, 10], "l": [1, 2, 3, 9, 10, 19, 20, 24, 36], "layer": [1, 9, 10], "leaf": [1, 9, 10], "step": [1, 2, 9, 10, 13, 14, 18, 20, 25, 42, 56, 57], "back": [1, 9, 10], "root": [1, 9, 10, 12, 13, 25], "r": [1, 2, 3, 5, 9, 10, 14, 15, 18, 20, 22, 24, 25, 33, 36, 42, 45, 46, 48, 49, 50, 53, 54, 56, 57], "c": [1, 2, 9, 10, 27], "p": [1, 9, 10, 24, 48, 49], "pp": [1, 9, 10], "mbp": [1, 9, 10], "pm": [1, 9, 10], "mark_sequ": [1, 9, 10], "mark": [1, 9, 10, 19, 31, 37, 44], "mark_path": [1, 9, 10], "markp": [1, 9, 10], "clear": [1, 2, 9, 10, 19, 43, 51], "bestseq": [1, 9, 10], "bestseqd": [1, 9, 10], "single_node_str": [1, 9, 10], "preferred_act": [1, 9, 10], "path": [1, 9, 10, 13, 18, 34], "path_to": [1, 9, 10], "tree_stat": [1, 9, 10], "left": [1, 9, 10, 18, 20, 25, 36, 42, 44, 56, 57], "up": [1, 5, 9, 10, 12, 36], "right": [1, 9, 10, 18, 20, 25, 36, 42, 43, 44, 56, 57], "down": [1, 9, 20], "longleft": [1, 9], "longright": [1, 9], "hline": [1, 9], "vline": [1, 9], "bottomleft": [1, 9], "longbottomleft": [1, 9], "topleft": [1, 9], "longtopleft": [1, 9], "topright": [1, 9], "longtopright": [1, 9], "bottomright": [1, 9], "longbottomright": [1, 9], "intersect": [1, 9], "topt": [1, 9], "leftt": [1, 9], "rightt": [1, 9], "bottomt": [1, 9], "shadebar": [1, 9], "subscript": [1, 9], "reward_func": [1, 9], "endc": [1, 9], "disabl": [1, 9], "exist": [2, 9, 10, 16, 18, 20, 23, 24], "solver": [2, 14, 16, 19, 20, 24, 56], "under": [2, 13, 18, 20, 27, 47], "develop": [2, 5, 18, 22, 24, 25, 27], "contribut": [2, 21, 24, 25], "want": [2, 13, 19, 43], "po": [2, 24, 35, 48, 49], "baselin": 2, "paper": [2, 3, 17, 19, 20, 24, 31, 33, 35, 36, 37, 42, 44, 46, 52, 54], "2": [2, 9, 10, 17, 18, 20, 24, 25, 27, 33, 35, 36, 44, 48, 49, 50, 51, 53, 54, 55], "quot": [2, 20, 31, 33, 35, 36, 37, 56, 57], "from": [2, 5, 8, 9, 10, 13, 14, 17, 18, 19, 20, 25, 31, 33, 35, 36, 37, 43, 44, 45, 46, 47, 51, 54, 56, 57], "To": [2, 9, 10, 13, 17, 19, 20, 36, 57], "provid": [2, 18, 19, 20, 23, 24, 27], "perform": [2, 3, 5, 18, 20, 27], "benchmark": 2, "case": [2, 7, 18, 20, 21, 24, 27, 42, 45, 46, 56, 57], "we": [2, 13, 16, 18, 19, 20, 21, 24, 25, 27, 31, 42, 43, 46, 47], "evalu": [2, 8], "simpl": [2, 16, 19, 20, 24, 31, 44, 46, 47, 48, 49, 50, 56], "mont": [2, 20], "carlo": [2, 20], "simul": [2, 5, 14, 18, 20, 42, 45, 56], "without": [2, 18, 19, 20], "ani": [2, 8, 18, 37, 45, 46], "tree": [2, 9, 10, 12, 14, 19, 20, 25], "The": [2, 3, 5, 8, 9, 10, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 27, 31, 33, 35, 36, 37, 38, 42, 44, 45, 46, 47, 48, 49, 50, 52, 54, 56, 57], "us": [2, 3, 5, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17, 19, 20, 21, 22, 24, 25, 27, 31, 35, 42, 43, 44, 45, 46, 47, 56], "describ": [2, 3, 5, 13, 15, 16, 17, 19, 20, 24, 42, 45], "section": [2, 19, 20], "3": [2, 9, 10, 18, 20, 25, 27, 36, 44, 45, 48, 49, 56, 57], "It": [2, 3, 5, 8, 9, 10, 14, 17, 18, 19, 20, 24, 27, 44, 46], "n": [2, 7, 8, 9, 10, 18, 19, 35, 42, 44, 48, 49], "A": [2, 3, 5, 9, 10, 14, 15, 18, 19, 20, 22, 24, 27, 31, 36, 37, 42, 43, 45, 51, 56, 57], "each": [2, 3, 5, 8, 9, 10, 18, 36, 37, 45, 46], "legal": 2, "select": 2, "highest": [2, 5, 8, 9, 10, 55], "averag": [2, 8], "return": [2, 3, 5, 7, 8, 9, 10, 14, 17, 18, 20, 35, 36, 43, 45, 46, 47, 48, 49, 54, 55, 56, 57], "don": [2, 5, 7, 20, 42], "requir": [2, 5, 7, 9, 14, 15, 25, 36, 46, 48, 49, 54, 56, 57], "an": [2, 3, 5, 8, 9, 14, 15, 17, 18, 19, 20, 22, 24, 27, 31, 33, 35, 36, 37, 42, 43, 44, 45, 46, 47, 48, 49, 50, 53, 56, 57], "But": [2, 5, 7, 13, 14, 20, 42, 44, 46, 56, 57], "do": [2, 5, 13, 19, 20, 31], "class": [2, 3, 5, 8, 9, 10, 14, 15, 17, 18, 19, 20, 23, 31, 33, 34, 35, 36, 38, 39, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57], "base": [2, 3, 5, 7, 8, 9, 10, 13, 18, 19, 20, 23, 24, 27, 31, 33, 34, 35, 36, 38, 39, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57], "self": [2, 5, 8, 9, 10, 17, 19, 20, 35, 36, 43, 45, 46, 48, 49, 54, 55, 56, 57], "carri": [2, 5], "inform": [2, 3, 5, 13, 15, 20, 47, 51], "bt": [2, 3, 5, 35], "ht": [2, 5], "o": [2, 5, 7, 9, 13, 15, 18, 20, 22, 24, 36, 48, 49, 54, 56, 57], "g": [2, 3, 5, 14, 20, 21, 33, 35, 37, 42, 45, 56], "pi": [2, 5, 15, 20, 36, 46, 48, 49, 57], "necessari": [2, 5, 19, 42], "rollout_polici": [2, 9, 10, 20], "given": [2, 5, 7, 8, 9, 10, 12, 15, 17, 18, 20, 36, 42, 45, 46, 57], "one": [2, 5, 9, 10, 16, 20, 24, 27, 36, 43, 45, 56, 57], "real_act": [2, 5, 7, 42, 51], "real_observ": [2, 5, 7, 20, 42, 51], "real": [2, 5, 7, 18, 20, 42, 45, 53], "accordingli": [2, 5], "If": [2, 3, 5, 7, 8, 9, 10, 12, 18, 20, 24, 43, 45, 46, 51, 56, 57], "i": [2, 3, 5, 7, 8, 9, 10, 12, 13, 14, 15, 17, 18, 19, 20, 21, 24, 25, 27, 31, 33, 35, 36, 37, 38, 42, 43, 44, 45, 46, 47, 48, 49, 53, 54, 56, 57], "also": [2, 5, 9, 10, 19, 20, 22, 24, 27, 56, 57], "here": [2, 5, 9, 10, 13, 17, 18, 20, 21, 25, 31], "attribut": [2, 5, 44], "should": [2, 3, 5, 7, 13, 14, 15, 18, 19, 20, 23, 25, 44, 46], "set": [2, 5, 7, 8, 9, 14, 17, 18, 19, 20, 27, 36, 43, 44, 45, 47, 48, 49, 54, 56, 57], "true": [2, 5, 7, 8, 9, 10, 12, 14, 18, 20, 25, 37, 42, 45, 46, 47, 50, 56], "By": [2, 5, 18, 47], "default": [2, 5, 7, 14, 18, 56], "doe": [2, 5, 8, 9, 10, 14, 15, 18, 20, 27, 37, 47, 54], "noth": [2, 5], "function": [2, 3, 5, 7, 8, 9, 10, 14, 17, 18, 20, 22, 31, 35, 42, 43, 45, 51], "thi": [2, 3, 5, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17, 18, 20, 24, 25, 27, 31, 34, 35, 36, 42, 43, 44, 45, 46, 47, 48, 49, 50, 53, 54, 56, 57], "uct": 2, "partial": [2, 20, 24, 36, 37, 56, 57], "present": [2, 8, 31], "extens": [2, 20, 21, 24, 27, 44, 46, 50], "combin": [2, 9, 12], "mct": [2, 25], "ucb1": [2, 14], "In": [2, 16, 17, 18, 19, 20, 21, 31, 42, 54, 56, 57], "other": [2, 20, 24, 48, 49, 56, 57], "word": 2, "just": [2, 8, 9, 18, 20, 25, 33, 38, 43, 56, 57], "arbitrari": 2, "strategi": 2, "mai": [2, 5, 7, 13, 15, 16, 19, 24, 25, 31, 42], "refer": [2, 3, 13, 14, 17, 31, 35, 48, 56, 57], "spars": 2, "poss": 2, "introduc": [2, 19, 20, 36, 37], "recent": 2, "5": [2, 3, 9, 10, 18, 20, 25, 35, 45, 47, 48, 49, 56], "mdp": [2, 5, 24, 27], "6": [2, 9, 10, 18, 20, 25, 50], "propos": 2, "call": [2, 5, 7, 18, 20], "powss": 2, "howev": [2, 20], "line": [2, 18, 19], "work": [2, 9, 10, 12, 14, 18, 20, 24, 25, 27], "sole": 2, "still": [2, 7, 20], "compar": [2, 8], "exactli": 2, "while": [2, 14, 20, 36, 56, 57], "depend": [2, 3, 5, 9, 14, 31, 35, 54], "explor": [2, 9, 10], "constant": [2, 9, 28, 29], "7": [2, 9, 10, 14, 18], "reflect": 2, "prior": [2, 5, 14, 20, 42, 43, 50, 51, 56], "knowledg": [2, 20], "regard": [2, 5, 14, 20], "amount": [2, 31], "thei": [2, 7, 18, 43, 47], "follow": [2, 3, 5, 9, 10, 17, 18, 19, 20, 24, 25, 35, 42, 56, 57], "wa": [2, 14, 19], "r_": 2, "hi": 2, "lo": 2, "where": [2, 3, 5, 7, 9, 19, 20, 25, 31, 35, 42, 44, 45, 46, 48, 49], "rhi": 2, "achiev": 2, "dure": [2, 9, 10, 14, 17, 18, 20, 47], "run": [2, 13, 14, 18, 19, 20, 25, 47, 56, 57], "0": [2, 5, 8, 9, 10, 17, 18, 20, 25, 34, 35, 36, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 53, 54, 55, 56], "rlo": 2, "lowest": 2, "inde": [2, 20], "differ": [2, 13, 14, 15, 19, 27, 36, 42, 44, 46], "between": [2, 5, 9, 14, 15, 19, 27, 36, 45, 47, 56], "certainli": 2, "onli": [2, 5, 9, 10, 12, 14, 15, 20, 37, 46, 56], "wai": [2, 18, 20, 27], "obtainx1": 2, "object": [2, 5, 9, 10, 14, 17, 20, 23, 24, 25, 28, 29, 34, 43, 44, 45, 46, 47, 48, 49, 53, 55], "problem": [2, 3, 5, 7, 13, 16, 18, 20, 21, 24, 25, 27, 28, 29, 31, 33, 36, 37, 38, 43, 45, 48, 49, 52, 54, 56, 57], "specif": [2, 5, 8, 9, 10, 14, 20, 27], "cl": [2, 5], "kwarg": [2, 5, 8, 9, 10, 14, 35, 36, 43, 44, 45, 46, 48, 49, 50, 53, 55, 57], "intend": 2, "classmethod": [2, 5, 8, 18, 44, 46, 53, 54, 55], "mimic": 2, "behavior": [2, 14, 20, 44], "generateleg": 2, "generatepref": 2, "david": [2, 20], "silver": [2, 20], "code": [2, 5, 9, 14, 17, 18, 19, 20, 24, 27], "tupl": [2, 3, 5, 8, 9, 43, 45, 46, 48, 49, 54], "form": [2, 7], "num_visits_init": 2, "value_init": 2, "repres": [2, 3, 5, 7, 8, 9, 10, 16, 18, 19, 43, 48, 49], "prefer": [2, 9, 10, 14, 20], "act": [2, 5, 20, 24, 25, 56], "despot": [2, 27, 50], "For": [2, 5, 8, 12, 14, 20, 25, 45, 47, 50], "exampl": [2, 5, 9, 10, 14, 17, 19, 20, 21, 22, 24, 42, 45, 47, 56, 57], "certain": [2, 5], "possibl": [2, 5, 9, 20, 27, 36, 44, 46, 48, 49, 54, 56, 57], "subset": [2, 9, 10], "all": [2, 5, 8, 9, 10, 14, 20, 27, 35, 36, 43, 46, 48, 49, 54, 56, 57], "when": [2, 5, 8, 9, 10, 13, 14, 16, 17, 18, 19, 20, 24, 25, 27, 42, 48, 49, 52, 54], "domain": [2, 9, 14, 16, 19, 24, 28, 31, 34, 35, 42, 46, 48, 50, 56], "can": [2, 5, 9, 10, 14, 18, 19, 20, 22, 25, 27, 31, 36, 38, 42, 44, 45, 46, 52, 56, 57], "heurist": [2, 20, 48, 49], "space": [2, 3, 5, 7, 14, 18, 19, 20, 22, 31, 33, 34, 35, 36, 37, 43, 44, 46, 48, 49, 52, 56, 57], "enumer": [2, 9, 10, 14, 15, 18, 20, 22, 56], "__init__": [2, 5, 8, 13, 14, 17, 19, 20], "max_depth": [2, 9, 10, 12, 20, 42, 50], "planning_tim": [2, 14, 20, 42, 50], "1": [2, 3, 5, 8, 9, 10, 12, 17, 18, 19, 20, 24, 25, 31, 34, 35, 36, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 53, 54, 56, 57], "num_sim": [2, 9, 10, 14], "discount_factor": [2, 5, 9, 10, 18, 20, 42, 50], "9": [2, 9, 14, 18, 20, 25], "exploration_const": [2, 9, 10, 20, 42, 50], "sqrt": 2, "action_prior": [2, 17], "none": [2, 3, 5, 7, 8, 9, 10, 12, 17, 18, 20, 25, 34, 42, 43, 44, 46, 48, 49, 53, 54, 56], "show_progress": 2, "fals": [2, 5, 7, 9, 12, 18, 25, 33, 35, 36, 42, 43, 45, 46, 47, 48, 49, 53, 55, 56, 57], "pbar_update_interv": 2, "paramet": [2, 3, 5, 7, 8, 9, 10, 14, 18, 20, 35, 36, 42, 43, 45, 46, 48, 49, 51, 54, 56, 57], "int": [2, 9, 10, 18, 43, 45, 56, 57], "float": [2, 5, 8, 9, 18, 36, 45, 46, 48, 49, 54, 56, 57], "time": [2, 7, 18, 19, 36, 42, 44, 48, 49], "second": [2, 7, 9, 10, 13, 18, 19], "neg": [2, 14, 20, 56, 57], "number": [2, 5, 7, 8, 9, 10, 12, 14, 18, 27, 35, 42, 43, 56, 57], "reach": [2, 5, 18, 20, 42], "both": [2, 9, 10, 18, 19, 56, 57], "ar": [2, 5, 7, 8, 9, 10, 13, 14, 15, 18, 19, 20, 21, 25, 27, 31, 35, 36, 42, 43, 46, 47, 48, 49, 52, 56, 57], "over": [2, 7, 8, 15, 16, 17, 20, 31, 43, 56], "bool": [2, 5, 7, 9, 10, 18, 42, 45, 56], "print": [2, 9, 10, 14, 18, 20], "progress": [2, 14], "bar": [2, 14, 35], "after": [2, 5, 14, 18, 20, 36, 44, 45, 46, 53], "you": [2, 5, 7, 9, 10, 13, 14, 17, 18, 19, 20, 24, 25, 31, 42, 56, 57], "even": [2, 21], "your": [2, 14, 19, 24], "stop": 2, "criteria": 2, "ran": 2, "last": [2, 37, 44], "assum": [2, 3, 5, 8, 9, 14, 18, 25, 31, 33, 34, 35, 36, 43, 46, 47, 48, 49, 54, 56, 57], "ha": [2, 5, 8, 13, 18, 19, 23, 27, 42, 47, 48, 49, 55], "been": [2, 20, 21], "take": [2, 5, 8, 14, 17, 18, 19, 20, 38, 48, 49, 52], "receiv": [2, 5, 19, 20, 36, 48, 49, 56, 57], "choos": [2, 17, 20], "uniformli": [2, 20], "child": 2, "implement": [2, 3, 5, 8, 9, 14, 16, 17, 20, 21, 22, 23, 24, 27, 31, 36, 37, 42, 46, 48, 49, 52, 54, 56, 57], "origin": [2, 17, 19, 20, 24, 31, 33, 34, 35, 36, 37, 44, 46, 48, 49, 50], "larg": [2, 5, 20, 52, 53, 54], "http": [2, 3, 18, 24, 25], "nip": 2, "cc": 2, "4031": 2, "One": [2, 20, 43], "thing": 2, "happen": [2, 42, 46], "new": [2, 5, 7, 8, 14, 24, 45, 53], "store": [2, 5, 9, 18, 20], "level": [2, 19], "execut": [2, 5, 9, 10, 18, 20, 45, 47], "next": [2, 5, 9, 20, 35, 36, 46, 48, 49, 54, 56, 57], "These": 2, "reinvigor": [2, 7, 25], "enough": [2, 21, 36, 57], "separ": [2, 13, 19], "complet": [2, 9, 18, 31], "node": [2, 9, 10, 12, 14, 18], "longer": 2, "keep": [2, 7, 9, 36, 57], "track": [2, 7], "reinvogr": 2, "onc": [2, 5, 20, 56], "have": [2, 3, 5, 7, 8, 9, 10, 14, 15, 18, 19, 20, 21, 27, 42, 43, 45, 48, 49, 56, 57], "previous": [2, 14, 19], "version": [2, 18, 25], "basicpomcp": 2, "jl": [2, 18, 27], "github": [2, 13, 14, 18, 24, 25], "com": [2, 18, 25], "juliapomdp": [2, 31], "two": [2, 8, 9, 13, 16, 18, 20, 27, 56, 57], "equival": [2, 9, 20], "gener": [2, 5, 8, 13, 15, 17, 18, 19, 20, 21, 24, 42, 56, 57], "doesn": [2, 27, 43, 56, 57], "hurt": [2, 20, 56, 57], "featur": [2, 9, 10, 24, 27], "state_transform_func": [2, 7], "artifici": [2, 20, 24], "transform": 2, "signatur": [2, 14], "s_transform": 2, "maintain": [2, 5, 7, 18, 36], "iter": [2, 7, 14, 18, 20, 25, 27, 48, 49, 50, 56], "explain": [2, 13], "4": [2, 3, 9, 10, 18, 20, 25, 44], "stochast": [2, 20, 24, 37, 56], "No": [2, 18], "prune": [2, 18], "explod": 2, "veri": [2, 5, 20], "fast": 2, "feasibl": [2, 5, 9, 36, 48, 49, 54, 56, 57], "small": [2, 14, 20, 36, 46, 50, 51, 53, 54, 56, 57], "explicitli": [2, 7, 15, 17, 18, 20, 22, 48, 49], "horizon": [2, 14, 18, 20], "inf": [2, 18], "epsilon": [2, 8, 9, 35, 42, 43, 46], "1e": [2, 8, 9, 20, 35, 46], "lqr": [2, 3], "maximum": [2, 3, 14, 18, 31, 33, 34, 35, 42, 43, 56, 57], "likelihood": [2, 3, 8, 31, 33, 34, 35], "func_sysd": [2, 3], "func_ob": [2, 3], "jac_sysd": [2, 3], "jac_ob": [2, 3], "jac_sysd_u": [2, 3], "noise_ob": [2, 3], "noise_sysd": [2, 3], "qlarg": [2, 3], "q": [2, 3, 9, 10, 14], "planning_horizon": [2, 3], "15": [2, 3, 9, 10, 18, 20, 56], "sourc": [2, 3, 7, 9, 10, 12, 13, 18, 19, 20, 25, 31, 33, 34, 35, 36, 38, 39, 42, 43, 44, 45, 46, 47, 48, 50, 51, 52, 53, 54, 55, 56], "ut": [2, 3, 35], "ekf": [2, 3], "equat": [2, 3, 7], "12": [2, 3, 9, 18, 25, 45, 53], "13": [2, 3, 14], "f": [2, 3, 9, 35], "point": [2, 3, 18, 47, 50, 52, 54], "mt": [2, 3, 35], "cov_t": [2, 3], "np": [2, 3], "arrai": [2, 3, 8, 9, 35], "shape": [2, 3, 9, 19, 44, 46, 47], "cost": [2, 3, 7, 43, 48, 49], "need": [2, 3, 7, 17, 18, 20, 25, 31, 43, 46, 56, 57], "turn": [2, 3], "long": [2, 3], "vector": [2, 3, 8, 9, 18, 33, 35], "consist": [2, 3, 36, 57], "column": [2, 3], "stich": [2, 3], "togeth": [2, 3], "control": [2, 3, 20, 33, 45, 46, 53], "noise_t": [2, 3], "nois": [2, 3, 9, 20, 35, 48, 49, 56, 57], "possibli": [2, 3], "matrix": [2, 3], "wt": [2, 3], "term": [2, 3], "e": [2, 3, 5, 9, 10, 14, 19, 20, 21, 25, 35, 36, 42, 44, 45, 46, 47, 48, 49, 54, 56, 57], "ad": [2, 3, 5, 14], "system": [2, 3, 18, 20, 27, 33, 35], "dynam": [2, 3, 35, 46, 47], "v": [2, 3, 9, 10, 14, 18], "eq": [2, 3], "sam": [2, 3], "dimension": [2, 3, 36], "noise_obs_cov": [2, 3], "correspond": [2, 3, 17, 18, 45], "b_i": [2, 3], "u_i": [2, 3], "num_seg": [2, 3], "18": [2, 3, 9, 10, 18], "phi": [2, 3], "sum": [2, 3], "b_": [2, 3, 7, 20], "b_t": [2, 3, 20], "seg": [2, 3], "essenti": [2, 3, 15], "bu_traj": [2, 3], "b_de": [2, 3], "u_d": [2, 3], "17": [2, 3], "desir": [2, 3, 13], "covt": [2, 3], "comput": [2, 3, 7, 14, 18, 43], "list": [2, 3, 8, 9, 10, 14, 18], "begin": [2, 3, 9, 20], "segment": [2, 3], "avail": [2, 3, 5, 14, 24], "pass": [2, 3, 5, 18, 20, 36], "empti": [2, 3, 51], "b_0": [2, 3], "u_init": [2, 3], "control_bound": [2, 3], "opt_opt": [2, 3], "opt_callback": [2, 3], "solv": [2, 3, 14, 16, 19, 22, 24, 25, 28, 36, 37, 42, 50, 56], "sqp": [2, 3], "direct": [2, 3, 23], "transcript": [2, 3], "produc": [2, 3], "doc": [2, 3, 14], "scipi": [2, 3], "org": [2, 3, 14, 18, 24, 25], "tutori": [2, 3, 14, 17], "optim": [2, 3, 20], "html": [2, 3, 13, 18, 25], "opt_r": [2, 3], "lesli": [2, 20, 24], "pack": [2, 20, 24], "kaelbl": [2, 20, 24], "michael": [2, 19, 20, 24], "littman": [2, 20, 24], "anthoni": [2, 18, 20, 22, 24], "cassandra": [2, 18, 20, 22, 24], "intellig": [2, 20, 24], "101": [2, 20, 24], "99": [2, 18, 20, 24, 42, 50], "134": [2, 20, 24], "1998": [2, 20, 24], "joel": [2, 20], "veness": [2, 20], "advanc": [2, 20, 27], "neural": [2, 20], "process": [2, 20, 35, 56, 57], "2164": [2, 20], "2172": [2, 20], "2010": [2, 20], "levent": 2, "kocsi": 2, "csaba": 2, "szepesv": 2, "\u00e1": 2, "ri": 2, "bandit": 2, "european": 2, "confer": [2, 19, 20, 24], "machin": [2, 18], "learn": [2, 5, 15, 20, 21, 23, 24, 27], "282": 2, "293": 2, "springer": 2, "2006": 2, "platt": 2, "tedrak": 2, "lozano": 2, "perez": 2, "proceed": [2, 20], "robot": [2, 19, 20, 24, 27, 31, 33, 35, 38, 42, 43, 44, 45, 46, 47, 48, 49, 52, 54], "scienc": 2, "zaragoza": 2, "spain": 2, "june": 2, "doi": 2, "10": [2, 9, 10, 14, 18, 20, 24, 42, 45, 48, 49, 50, 51, 53, 54, 56, 57], "15607": 2, "rss": 2, "vi": [2, 20], "037": 2, "h": [2, 20], "lim": 2, "clair": 2, "j": 2, "tomlin": 2, "zachari": 2, "sunberg": 2, "search": [2, 9, 10, 12, 14, 20, 24, 25, 28, 29, 36, 37, 43, 44, 46, 48, 49], "guarante": 2, "continu": [2, 14, 20, 31, 33, 35], "arxiv": [2, 24], "preprint": 2, "1910": 2, "04332": 2, "2019": [2, 19, 20, 42, 44, 46], "kearn": 2, "yishai": 2, "mansour": 2, "andrew": 2, "y": [2, 43, 44, 45, 46, 48, 49, 51, 52, 53], "ng": 2, "markov": [2, 20, 56, 57], "decis": [2, 20, 56, 57], "49": [2, 9], "193": 2, "208": 2, "2002": 2, "ant": 2, "\u00f3": 2, "nio": 2, "gusmao": 2, "tapani": 2, "raiko": 2, "toward": 2, "beyond": [2, 24], "game": 2, "go": [2, 13, 16, 25, 37], "ecai": 2, "384": 2, "389": 2, "2012": 2, "import": [5, 9, 10, 15, 17, 18, 20, 25], "must": [5, 18, 20, 31, 36, 37], "hashabl": [5, 9], "oper": 5, "its": [5, 14, 15, 18, 20, 22, 23, 27, 31, 36, 37, 38, 45, 46, 47, 48, 49, 56, 57], "job": [5, 15, 20], "taken": [5, 8, 42], "care": [5, 43], "suppli": [5, 17], "OR": 5, "policy_model": [5, 9, 10, 19, 20, 42, 50], "attr_nam": 5, "attr_valu": 5, "allow": [5, 14, 19, 20, 24], "sometim": [5, 20], "model": [5, 9, 14, 18, 19, 22, 23, 24, 28, 31, 33, 36, 42, 43, 44, 48, 49, 50, 56, 57], "transit": [5, 7, 9, 18, 19, 20, 35, 36, 45, 46, 48, 49, 54, 56, 57], "current": [5, 7, 9, 10, 18, 22, 37, 45, 48, 49], "which": [5, 7, 8, 9, 10, 14, 17, 18, 20, 27, 35, 38, 45, 56, 57], "most": [5, 8, 9, 35, 36, 43, 46, 48, 49, 54, 57], "like": [5, 8, 9, 10, 13, 14, 15, 19, 20, 25, 35, 36, 43, 46, 48, 49, 54, 57], "map": [5, 8, 9, 18, 40, 43, 44, 45, 46, 47, 51], "variabl": [5, 8, 18, 55, 56], "pr": [5, 7, 8, 9, 36, 46, 48, 49, 54, 56, 57], "x": [5, 8, 9, 25, 31, 33, 35, 36, 43, 44, 45, 46, 48, 49, 51, 52, 53], "varval": 5, "evaul": 5, "world": [5, 20, 25, 36, 42, 44, 45, 46, 56], "2d": [5, 14, 42, 44, 46, 47], "gridworld": [5, 19, 43, 44, 46], "render": 5, "pygam": [5, 25, 45, 53], "Or": [5, 8, 20, 25], "could": [5, 8, 16, 17, 20, 24, 25, 27, 42, 44, 45, 46, 56], "3d": 5, "opengl": 5, "therefor": [5, 7, 36], "mind": 5, "how": [5, 16, 19, 24, 56], "so": [5, 9, 10, 13, 14, 20, 25, 27, 35, 37], "passiv": 5, "never": [5, 54], "nor": [5, 20, 56, 57], "init_st": [5, 9, 18, 34, 36, 39, 45, 48, 49, 53], "next_stat": [5, 9, 20, 35, 36, 44, 45, 46, 48, 49, 54, 56, 57], "appli": [5, 14], "assign": [5, 8], "underli": [5, 8, 35, 57], "accord": [5, 9, 19, 20, 35, 36, 46, 47, 48, 49, 52, 54, 56, 57], "type": [5, 7, 8, 9, 14, 17, 18, 35, 36, 43, 45, 46, 48, 49, 54, 56, 57], "synonym": 5, "result": [5, 7, 20, 44, 45, 46], "trigger": [5, 45], "becom": [5, 20, 45], "discount": [5, 18, 25, 36, 48, 49], "until": [5, 18], "condit": [5, 20], "reward": [5, 9, 18, 19, 20, 25, 36, 45, 46, 48, 49, 54, 56, 57], "addition": [5, 25], "exhibit": 5, "properti": [5, 9, 10, 14, 34, 44, 45, 47, 48, 49, 53], "That": [5, 18], "support": [5, 8, 15, 17, 23, 24, 27, 46], "dictionari": [5, 8, 9, 20, 43], "randomli": [5, 8, 9, 19, 35, 36, 46, 48, 49, 54, 56, 57], "tempor": 5, "abstract": [5, 8], "defin": [5, 8, 9, 14, 16, 17, 18, 19, 22, 23, 33, 34, 35, 36, 37, 38, 42, 44, 46], "semi": 5, "reinforc": [5, 23, 27], "satisfi": 5, "conveni": [5, 9, 14], "overriden": 5, "feel": [5, 27], "write": [5, 18], "boolean": 5, "whether": [5, 15, 18, 36], "technic": 5, "instanc": [5, 18, 19, 45, 48, 49, 56, 57], "env": [5, 18, 19, 20, 28, 31, 42, 50], "name": [5, 9, 18, 20, 36, 44, 48, 56, 57], "treat": [5, 20, 43, 56], "h_t": [5, 20], "reason": 5, "accommod": 5, "vari": [5, 31, 44, 46], "probabilti": 5, "arg": [5, 9, 10, 14, 20, 36, 48, 49, 54, 56, 57], "pair": 5, "mathbb": [5, 33], "denot": 5, "sim": [5, 20], "black": [5, 9], "box": 5, "creat": [5, 9, 10, 13, 18, 19, 20, 31, 56], "n_step": 5, "compon": [5, 18, 19, 20, 40, 50, 54], "oo": [5, 14, 19, 23, 44, 53], "As": [5, 17, 19], "main": [5, 18, 20, 28, 36, 48, 49, 50, 56, 57], "benefit": 5, "reduc": [5, 7, 44], "scale": 5, "exponenti": 5, "linear": [5, 35], "increas": 5, "see": [5, 8, 14, 15, 18, 19, 20, 21, 22, 24, 25, 50], "alwai": [5, 21, 37], "objid": [5, 42, 43, 44, 45, 46], "alia": [5, 9, 10], "return_oost": [5, 14, 43], "z": [5, 7, 45, 53], "mapsto": 5, "z_1": 5, "cdot": [5, 18, 35], "z_n": 5, "id": [5, 43, 44, 45, 46], "dict": [5, 7, 8, 14, 43, 44, 45, 51], "object_observ": [5, 44], "singl": [5, 9, 10, 19, 44], "prod_i": 5, "z_i": 5, "param": [5, 44], "again": 5, "chang": [5, 8, 14, 15, 20, 25, 35, 44, 46], "directli": [5, 7, 20, 22, 36, 57], "object_st": [5, 44, 46], "becaus": [5, 13, 15, 18, 20, 36, 37, 43], "caus": 5, "hashcod": 5, "incorrect": [5, 9], "kei": [5, 9, 10], "attr": 5, "request": [5, 31], "frozenset": 5, "identifi": 5, "sinc": [5, 7, 20], "hash": [5, 9, 14], "s_i": [5, 44], "made": [5, 7, 25], "str": [5, 8, 18, 45, 56], "onlin": [5, 20, 31, 50], "pure": 5, "underneath": 5, "hood": 5, "Its": 5, "output": [5, 13, 18, 25], "expect": [5, 18, 25], "same": [5, 7, 8, 14, 18, 20, 52, 54, 56], "current_histogram": 7, "state_mapp": [7, 8], "oarg": 7, "targ": 7, "normal": [7, 8, 36, 46, 48, 49, 57], "static_transit": 7, "next_state_spac": 7, "determinist": [7, 9, 20, 35, 46, 47, 48, 49, 54], "sum_": 7, "addit": [7, 18, 21, 24], "indic": [7, 35, 45], "thu": [7, 19, 44], "help": [7, 9, 10, 18, 19, 24], "avoid": [7, 14, 15, 47], "nest": 7, "alreadi": [7, 23], "prohibit": 7, "consid": [7, 19, 42, 45], "effici": 7, "contain": [7, 9, 10, 13, 14, 18, 20, 22, 27, 47, 56, 57], "part": [7, 18], "know": [7, 37, 42], "num_particl": [7, 8, 36, 42, 43, 48, 49, 50, 51], "simpli": [7, 20], "At": [7, 35], "least": 7, "more": [7, 9, 10, 13, 16, 17, 18, 19, 20, 21, 23, 24, 25, 27, 56, 57], "ok": 7, "current_particl": 7, "either": [7, 14, 18, 19, 20, 56, 57], "todo": [7, 14], "test": [7, 9, 14, 18, 28, 29], "prob": 8, "09": [8, 35, 46], "unweight": 8, "inherit": [8, 14, 20], "1000": [8, 42, 46, 50], "approxim": [8, 27, 52, 54], "feed": 8, "through": [8, 9, 10, 17, 20, 36, 42], "multipl": [8, 23], "interpret": [8, 19, 42, 44, 45], "those": [8, 20, 25], "approx_method": 8, "distance_func": 8, "drawn": 8, "nearest": 8, "queri": 8, "match": [8, 14], "closest": 8, "exact": [8, 14, 20, 36], "uniqu": 8, "aggreg": 8, "numer": [8, 18, 27], "densiti": 8, "multivari": 8, "Not": [8, 37], "isn": 8, "arbitrarili": 8, "deal": [9, 34], "percent": 9, "rgb": 9, "255": [9, 45, 53], "hx": 9, "string": [9, 10, 18, 42, 45, 57], "len": [9, 17], "ctype": 9, "cython": [9, 14, 24, 25, 27, 28, 29], "dct": 9, "make": [9, 10, 13, 14, 15, 19, 24, 25, 27, 37, 43], "easier": [9, 10, 14], "core": [9, 10, 15], "incorpor": [9, 10], "design": [9, 10, 24], "eas": [9, 10], "pdb": [9, 10, 56], "ipdb": [9, 10], "session": [9, 10], "minim": [9, 10], "usag": [9, 10], "pomdp_problem": [9, 10, 14, 18, 19, 21, 24, 25], "tiger": [9, 10, 14, 17, 18, 19, 24, 25, 28, 29], "tigerproblem": [9, 10, 18, 20, 28, 56, 57], "suppos": [9, 10], "too": [9, 10], "95": [9, 10, 18, 20, 36, 48, 49], "4096": [9, 10], "200": [9, 10], "tiger_problem": [9, 10, 14, 18, 20, 28, 29], "dd": [9, 10, 56], "set_trac": [9, 10], "program": [9, 10, 18, 22], "enter": [9, 10], "debugg": [9, 10, 12], "_vnodepp": [9, 10], "4095": [9, 10], "19": [9, 10, 18], "529": [9, 10], "\u2080listen": [9, 10], "_qnodepp": [9, 10], "4059": [9, 10], "\u2080tiger": [9, 10], "2013": [9, 10], "16": [9, 10], "586": [9, 10], "1883": [9, 10], "1441": [9, 10], "8": [9, 10, 14, 18, 25, 36, 54], "300": [9, 10], "out": [9, 10, 18, 19, 27], "entir": [9, 10, 20, 56, 57], "\u2081open": [9, 10], "139": [9, 10], "847": [9, 10], "\u2082open": [9, 10], "112": [9, 10, 18], "57": [9, 10], "191": [9, 10], "text": [9, 10, 18], "retriev": [9, 10], "subtre": [9, 10], "index": [9, 10, 18, 24], "listen": [9, 10, 14, 18, 20, 25, 56, 57], "2044": [9, 10], "160": [9, 10], "open": [9, 10, 18, 20, 56, 57], "148": [9, 10], "634": [9, 10], "20": [9, 10, 14, 18, 48], "237": [9, 10], "500": [9, 10, 42, 50], "obtain": [9, 10], "sequenc": [9, 10, 14, 20], "\u2081tiger": [9, 10], "1955": [9, 10], "947": [9, 10], "768": [9, 10], "022": [9, 10], "462": [9, 10], "395": [9, 10], "000": [9, 10], "247": [9, 10], "stand": [9, 10, 20, 24, 56, 57], "best": [9, 10, 14], "brows": [9, 10], "method": [9, 10, 14], "document": [9, 10, 14, 16, 18, 27], "futur": [9, 10], "organ": [9, 10, 19, 20], "kind": [9, 10], "total": [9, 10, 18], "start": [9, 10, 20, 25, 36, 37, 45], "largest": [9, 10], "edg": [9, 10, 18], "equal": [9, 10, 20, 48, 49, 56, 57], "as_debugg": [9, 10], "Will": [9, 10], "high": [9, 10, 19, 27], "huge": [9, 10], "interact": [9, 10, 15], "along": [9, 10], "move": [9, 10, 19, 25, 31, 36, 37, 48, 49, 54, 55], "parent": [9, 10, 45], "first": [9, 10, 13, 18, 19, 20, 25, 33, 35, 48, 49], "preset": [9, 10], "seq": [9, 10], "understand": [9, 10, 15], "_nodepp": [9, 10], "dest": [9, 10], "Such": [9, 10], "except": [9, 10, 45, 53], "static": [9, 10, 45, 46, 48, 49, 53, 56], "parent_edg": [9, 10], "indent": [9, 10], "include_children": [9, 10], "df": [9, 10], "gether": [9, 10], "statist": [9, 10], "about": [9, 10, 14, 19, 36, 43, 47, 48, 49], "colorstr": [9, 10], "assort": 9, "p1": [9, 47, 48, 49], "p2": [9, 47, 48, 49], "vec1": 9, "vec2": 9, "scalar": 9, "th": [9, 45, 47, 53], "dx": 9, "dy": 9, "dz": 9, "v1": 9, "v2": 9, "06": [9, 18], "python": [9, 14, 18, 19, 20, 24, 25, 27, 36, 50], "oldvalu": 9, "oldmin": 9, "oldmax": 9, "newmin": 9, "newmax": 9, "obj": 9, "arr": 9, "end": [9, 45], "48": 9, "8320": 9, "8321": 9, "50": [9, 18], "8322": 9, "51": [9, 18], "8323": 9, "52": [9, 18], "8324": 9, "53": 9, "8325": 9, "54": 9, "8326": 9, "55": 9, "8327": 9, "56": 9, "8328": 9, "8329": 9, "utilti": 9, "xval": 9, "yval": 9, "size": [9, 14, 18, 45, 47, 53], "label": 9, "connect": [9, 27, 42], "style": 9, "linewidth": 9, "xlabel": 9, "ylabel": 9, "loc": 9, "lower": [9, 45], "bbox_inch": 9, "tight": 9, "vert": 9, "ax": [9, 12], "edgecolor": 9, "verts0": 9, "verts1": 9, "verts_i": 9, "xy": [9, 44, 55], "vertic": 9, "numpi": [9, 35], "color0": 9, "color1": 9, "color_i": 9, "hex": 9, "charact": [9, 45], "xxxxxx": 9, "polygoncollect": 9, "axi": 9, "zorder": 9, "alpha": [9, 18], "linestyl": 9, "center": [9, 47], "radiu": [9, 45, 47], "fill": 9, "label_text": 9, "text_color": 9, "some": [9, 14, 16, 18, 20, 21, 25, 27, 42], "particular": 9, "data": 9, "piec": 9, "correct": [9, 15, 20], "typic": [9, 20], "tabular": [9, 14], "built": [9, 13, 14, 15], "specifi": [9, 13, 14, 17, 18, 20, 56, 57], "nextstat": 9, "emit": 9, "pattern": 9, "quickli": [9, 16, 24], "build": [9, 14, 15, 18, 19, 24, 25], "typographi": 9, "purpos": [9, 19, 24], "displai": [9, 12, 25], "them": [9, 16, 20, 25, 27, 43], "x1b": 9, "97m": 9, "96m": 9, "95m": 9, "94m": 9, "92m": 9, "93m": 9, "91m": 9, "1m": 9, "0m": 9, "shown": [9, 19, 35], "visualize_pouct_search_tre": 12, "visit_threshold": 12, "anonym": 12, "anonymize_act": 12, "anonymize_observ": 12, "output_fil": 12, "use_dot": 12, "visit": [12, 14, 17], "caveat": 12, "well": [12, 19, 20, 46, 56, 57], "shallow": 12, "larger": 12, "pleas": [12, 24], "custom": [12, 19], "herit": 12, "a1": 12, "a2": 12, "o1": 12, "o2": 12, "sphinx": [13, 14], "web": 13, "page": [13, 24, 25], "There": [13, 18, 20, 21, 25, 27, 31, 54], "Their": 13, "directori": [13, 25], "cd": 13, "py": [13, 14, 19, 20], "_sphinx_src": 13, "apidoc": 13, "api": 13, "rst": 13, "file": [13, 14, 19, 20, 25, 27, 42], "argument": [13, 14, 17], "re": [13, 20, 34, 45, 53, 56], "readm": 13, "read": [13, 20], "me": 13, "Then": [13, 20, 42], "includ": [13, 14, 15, 42, 43, 50], "top": [13, 14], "repositori": [13, 25], "websit": [13, 14, 25], "construct": [13, 18, 20, 42], "symbol": 13, "link": [13, 14, 18, 19, 24], "ln": 13, "cannot": [13, 36, 37], "access": [13, 20, 24], "remov": [13, 14, 18], "site": 13, "deploi": 13, "fundament": 15, "block": [15, 19, 36], "formal": 15, "encapsul": 15, "few": 15, "pomdp_pi": [14, 15, 16, 17, 19, 20, 21, 22, 23, 25, 27, 36, 50], "around": [15, 27], "convei": 15, "idea": [15, 20], "abov": [15, 18, 19, 20, 22, 25], "gist": [14, 15], "captur": 15, "versu": 15, "much": [14, 15], "sens": [15, 19, 45], "hold": [15, 51], "instead": [14, 15, 20, 42, 44, 46, 56, 57], "own": [14, 15, 46], "verifi": [14, 15, 25], "valid": [15, 46, 47], "diagram": 15, "langl": 15, "omega": [15, 18, 22, 33, 35], "rangl": 15, "discuss": 16, "simpler": [14, 16, 27, 42], "complic": [16, 19, 20, 24, 56, 57], "interest": 16, "former": 16, "latter": 16, "structur": [16, 19, 24], "project": [16, 19, 23, 24, 27], "convent": [16, 24, 47], "below": [17, 19, 21, 25], "minimum": [14, 17], "def": [17, 20], "rais": [17, 20], "notimplementederror": 17, "els": [17, 18, 20, 44, 46], "notion": 17, "narrow": 17, "express": 17, "detail": [17, 18, 19, 20, 22, 56], "paragraph": 17, "count": [17, 25, 45], "account": 17, "nu": [18, 22], "hope": [18, 21], "u": [18, 33, 35, 36], "mani": [18, 27], "librari": [14, 18, 22, 24, 25], "input": [18, 22, 44, 45], "written": [18, 20, 24, 27], "format": [14, 18, 20, 27], "pomdpx": [14, 18, 27], "pomdpconvert": 18, "toolkit": 18, "to_pomdp_fil": [14, 18], "to_pomdpx_fil": 18, "convers": [14, 18], "output_path": 18, "float_precis": [14, 18], "www": [18, 25], "spec": [18, 20, 56], "independ": 18, "blank": 18, "decim": 18, "order": [18, 20, 31, 33], "pomdpconvert_path": 18, "check": [18, 19, 20, 27, 48, 49], "adacompnu": 18, "instruct": [18, 25], "download": [18, 25], "ubuntu": 18, "04": 18, "gcc": 18, "bigbird": 18, "comp": 18, "edu": 18, "sg": 18, "pmwiki": 18, "farm": 18, "appl": [18, 27], "php": 18, "pomdpxdocument": 18, "binari": [18, 22], "let": [18, 20], "tigerst": [18, 28, 56, 57], "filenam": [18, 19], "test_tig": 18, "softwar": [18, 25, 27], "src": 18, "vi_prun": 18, "pomdp_solve_path": 18, "pomdp_nam": 18, "temp": 18, "remove_generated_fil": 18, "return_policy_graph": 18, "definit": [18, 20], "pomdp_solv": [14, 18], "compil": 18, "command": [18, 19, 25], "stop_criteria": 18, "weak": 18, "time_limit": 18, "pg": 18, "instal": [14, 18, 24], "appear": [18, 27, 31], "recommend": [18, 19, 25], "100": [18, 20, 36, 42, 43, 51, 56, 57], "rang": [18, 19, 20, 46, 47], "isinst": [18, 20], "cur_belief": [18, 20], "graph": [18, 19, 42, 44, 46], "new_belief": [18, 20], "pid": 18, "8239": 18, "mcgs_prune_freq": 18, "verbos": 18, "context": 18, "done": [18, 20, 27, 42], "epoch": 18, "00": 18, "sec": 18, "err": 18, "39": 18, "96": 18, "97": 18, "98": 18, "01": [18, 42, 43, 46], "40": 18, "solut": 18, "found": [18, 19, 25, 52], "user": [18, 20], "hr": 18, "min": 18, "lp_solv": 18, "report": 18, "lp": 18, "instabl": 18, "85": 18, "9697986575573173": 18, "03020134244268276": 18, "pomdpsol_path": 18, "timeout": 18, "30": [18, 45, 53], "memori": 18, "precis": [18, 31, 33], "logfil": 18, "anytim": [18, 50, 52, 54], "pomdpsol": 18, "limit": 18, "mb": 18, "regret": 18, "less": 18, "than": [18, 27], "finish": 18, "log": [14, 18], "stdout": 18, "stderr": 18, "_": 18, "000001": 18, "load": [14, 18, 24, 28, 29], "trial": [18, 28, 50], "backup": 18, "lbound": 18, "ubound": 18, "92": 18, "8205": 18, "821": 18, "2981": 18, "63": 18, "7547": 18, "70": 18, "0528": 18, "103": 18, "35722": 18, "3746": 18, "0174": 18, "155": 18, "44093": 18, "45": 18, "1431": 18, "38": [18, 28, 29], "7021": 18, "205": 18, "1184": 18, "36": 18, "4409": 18, "24": 18, "3225": 18, "1255": 18, "3714": 18, "13808e": 18, "21": 18, "41": 18, "1300": 18, "76277e": 18, "42": 18, "1350": 18, "75044e": 18, "43": 18, "1393": 18, "22729e": 18, "07": 18, "11": [18, 25], "target": [18, 19, 20, 42, 43, 45, 52, 54, 56], "extend": [14, 18, 19, 20, 21], "encod": 18, "alpha_path": 18, "pg_path": 18, "parse_pomdp_solve_output": 18, "pointer": 18, "incom": 18, "offlin": 18, "collect": 18, "associ": 18, "dot": 18, "product": 18, "lead": [18, 19], "domin": 18, "activ": [18, 27], "finit": [18, 20, 36, 37, 56], "max_": 18, "gamma": 18, "policy_path": 18, "parse_appl_policy_fil": 18, "involv": 19, "whose": 19, "better": 19, "mainten": 19, "readabl": 19, "task": [19, 23, 24, 27, 28, 29, 36], "rel": 19, "share": [19, 24], "wandzel": 19, "et": 19, "al": 19, "slightli": 19, "room": [19, 42], "topolog": [19, 42, 44, 46], "formul": 19, "orient": [19, 23, 37, 38, 42, 43, 44, 46, 47], "our": [19, 20, 27, 31, 47], "w": [19, 35, 44], "grid": [19, 36, 44, 46, 47, 48, 49, 54], "cell": [19, 52, 54], "three": [19, 20], "categori": 19, "motion": [19, 38, 42, 44, 46, 48, 49, 52], "look": [19, 25, 38, 44, 46], "region": [19, 45, 47], "find": [14, 19, 24, 25, 44, 46], "within": [19, 46, 47], "fan": [19, 44, 46, 47], "adjust": 19, "angl": [19, 45, 47], "laser": [19, 45, 47, 50], "scanner": [19, 45, 47], "360": [19, 47], "degre": [19, 45, 47], "sensor": [19, 20, 42, 43, 44, 45, 46, 48, 49], "disk": 19, "occlus": [19, 45, 47], "scan": [19, 45, 47], "beam": [19, 45, 47], "artifact": 19, "due": [14, 19, 47], "discret": [19, 31, 33], "figur": [19, 31, 35, 36], "screenshot": 19, "frame": 19, "imag": [14, 19], "circl": [19, 25], "perfect": [19, 46, 48, 49], "third": 19, "show": [14, 19, 24], "later": 19, "summari": 19, "procedur": [19, 20], "instanti": [19, 42], "good": [19, 25, 48, 49], "squeez": 19, "everyth": 19, "giant": 19, "might": [19, 20, 47, 56, 57], "reus": 19, "free": [19, 20, 23, 24, 27, 48, 49, 56, 57], "whatev": 19, "save": 19, "grid_map": [19, 42, 43, 46, 50, 51, 53, 54], "example_world": [19, 28, 29], "evid": 19, "role": 19, "mosoopomdp": [19, 28, 42], "logic": 19, "feedback": [19, 20, 56, 57], "loop": [19, 20, 56, 57], "m": [14, 19, 24, 25, 36, 50], "multi_object_search": [19, 25, 28, 29], "place": [19, 20, 36, 54], "obstacl": [19, 43, 45, 47], "pose": [19, 42, 44, 46, 47], "equip": [19, 46], "yet": [14, 19, 31, 37], "equip_sensor": [19, 42, 45], "make_laser_sensor": [19, 42, 45], "make_proximity_sensor": [19, 42, 45], "arthur": 19, "yoonseon": 19, "oh": 19, "fishman": 19, "nishanth": 19, "kumar": 19, "stefani": [19, 20, 24], "tellex": [19, 20, 24], "intern": [19, 20], "autom": [19, 20], "icra": [19, 42, 44, 46], "7194": 19, "7200": 19, "ieee": 19, "classic": [20, 48, 56, 57], "descript": [20, 31, 36, 37, 42, 44, 45, 46, 48, 49, 50, 56, 57], "introduct": [20, 56, 57], "kamalzadeh": [20, 56, 57], "hahsler": [20, 56, 57], "put": [20, 56, 57], "behind": [20, 56, 57], "door": [20, 56, 57], "treasur": [20, 56, 57], "front": [20, 47, 56, 57], "close": [20, 56, 57], "decid": [20, 56, 57], "get": [20, 25, 46, 50, 56, 57], "posit": [20, 31, 33, 34, 35, 37, 38, 48, 49, 54, 55, 56, 57], "awai": [20, 31, 54, 56, 57], "wait": [20, 56, 57], "neither": [20, 56, 57], "accur": [20, 56, 57], "hear": [20, 56, 57], "actual": [20, 31, 37, 42, 47, 56, 57], "vice": [20, 56, 57], "versa": [20, 56, 57], "encourag": 20, "valueerror": 20, "invalid": [20, 47], "__hash__": 20, "__eq__": 20, "side": [20, 36, 37], "boil": 20, "heard": 20, "growl": 20, "thresh": 20, "uniform": [20, 43, 48, 49, 50, 51, 56], "similarli": 20, "reset": [20, 56], "otherwis": [20, 36, 56], "stai": [14, 20, 54, 56], "startswith": 20, "choic": 20, "easili": 20, "tabl": 20, "flexibl": 20, "intract": 20, "determin": [20, 33, 47, 48, 49], "sever": [20, 21], "would": [14, 20, 27], "usual": 20, "human": 20, "engin": 20, "sort": 20, "guid": 20, "sure": [20, 43], "guidanc": 20, "caution": 20, "realli": [20, 43], "sai": 20, "inject": 20, "final": 20, "straightforward": 20, "commonli": 20, "_reward_func": 20, "elif": 20, "With": [20, 54], "abl": [14, 20], "mostli": 20, "obs_nois": [20, 56], "init_true_st": [20, 56, 57], "super": 20, "notic": 20, "constructor": 20, "now": [14, 20], "standard": 20, "a_t": 20, "s_t": 20, "rightarrow": 20, "s_": 20, "r_t": 20, "o_t": 20, "h_": 20, "cup": [20, 44], "unless": 20, "repeat": 20, "110": 20, "test_plann": [20, 28, 36, 48, 49, 56, 57], "nstep": [20, 36, 48, 49, 56, 57], "ennviron": 20, "skip": [14, 20], "estim": [20, 33], "percept": 20, "stack": 20, "saniti": 20, "come": 20, "extern": [14, 20, 22, 24, 25, 36, 57], "automat": 20, "num": 20, "short": 20, "abel": 20, "elli": 20, "hershkowitz": 20, "gabriel": 20, "barth": 20, "maron": 20, "stephen": 20, "brawner": 20, "kevin": 20, "farrel": 20, "jame": 20, "macglashan": 20, "goal": [20, 31, 37], "twenti": 20, "fifth": 20, "schedul": 20, "2015": 20, "yuchen": 20, "xiao": 20, "sammi": 20, "katt": 20, "andrea": 20, "ten": 20, "pa": 20, "shengjian": 20, "chen": 20, "christoph": 20, "amato": 20, "clutter": 20, "welcom": [21, 24], "light": [14, 21, 24, 28, 29, 33, 34, 35], "dark": [14, 21, 24, 28, 29, 33, 34, 35], "maze": 21, "multi": [14, 21, 23, 24, 25, 28, 29, 43, 44, 46], "sarsop": [14, 22, 25, 27], "rl": 23, "transfer": [23, 24], "research": [23, 24, 27], "baslin": 23, "comprehens": 24, "why": 24, "clean": 24, "intuit": 24, "relat": [24, 46], "peopl": 24, "commun": [24, 25, 27], "artial": 24, "bservabl": 24, "arkov": 24, "ecis": 24, "rocess": 24, "major": 24, "languag": 24, "what": 24, "changelog": 24, "mo": [14, 24, 25, 28, 29, 44], "principl": 24, "integr": [14, 24], "cite": 24, "inproceed": 24, "zheng2020pomdp_pi": 24, "titl": 24, "_py": 24, "author": 24, "zheng": 24, "kaiyu": 24, "booktitl": 24, "icap": 24, "2020": 24, "workshop": 24, "planrob": 24, "year": 24, "url": 24, "icaps20subpag": 24, "wp": 24, "upload": 24, "14": [24, 25, 36], "planrob_2020_paper_3": 24, "pdf": 24, "2004": [24, 48, 49], "10099": 24, "rocksampl": [14, 24, 25, 28, 29], "unload": [14, 24, 28, 29], "tag": [14, 24, 28, 29], "virtualenv": 25, "pip": [14, 25], "manag": 25, "offici": 25, "maco": 25, "On": 25, "window": [14, 25], "wiki": 25, "latest": 25, "releas": [14, 25], "clone": 25, "git": 25, "h2r": 25, "setup": [14, 25], "locat": [25, 36, 37, 43, 47, 48, 49, 52, 54], "pyx": [14, 25], "pyd": 25, "rebuild": 25, "messi": 25, "someth": [25, 44, 46], "66": 25, "bad": [25, 48, 49], "cumul": 25, "__num_sims__": 25, "1217": 25, "______id______": 25, "210": 25, "_____g": 25, "b_____": 25, "hello": 25, "xyth": [25, 44], "north": [25, 42, 44, 48, 49], "mosooobserv": [25, 42, 44, 45], "542": 25, "506": 25, "test_al": 25, "via": [25, 27], "hub": 25, "credit": 25, "romain": 25, "egel": 25, "think": 27, "peer": 27, "easi": 27, "ro": 27, "acceler": 27, "pomdpi": 27, "suffici": 27, "convolut": 27, "potenti": [14, 27], "clearer": 27, "pars": 27, "art": 27, "great": 27, "julia": 27, "known": [27, 48, 49], "suit": [27, 31], "analysi": 27, "besid": 27, "librai": 27, "port": 27, "ai": 27, "toolbox": 27, "bind": 27, "focus": 27, "lear": 27, "beliefmdp": 27, "belief_upd": [28, 42, 50, 51], "unittest": [28, 42, 45, 46, 50, 53], "random_world": [28, 42], "rocksample_problem": [28, 29], "rocktyp": [28, 48, 49], "moveact": [28, 48, 49], "sampleact": [28, 48, 49], "checkact": [28, 48, 49], "rstransitionmodel": [28, 48, 49], "rsobservationmodel": [28, 48, 49], "rsrewardmodel": [28, 48, 49], "rspolicymodel": [28, 48, 49], "rocksampleproblem": [28, 48, 49], "init_particles_belief": [28, 48, 49], "tigeract": [28, 56, 57], "tigerobserv": [28, 56, 57], "light_dark": [28, 29], "problem_discret": [28, 29], "discretelightdark": [28, 31], "load_unload": [28, 29], "lustat": [28, 36], "luaction": [28, 36], "luobserv": [28, 36], "luobservationmodel": [28, 36], "lutransitionmodel": [28, 36], "lurewardmodel": [28, 36], "lupolicymodel": [28, 36], "loadunloadproblem": [28, 36], "generate_random_st": [28, 36], "generate_init_belief": [28, 36], "experi": [28, 29, 31], "tagproblem": [28, 50], "local": 31, "plane": 31, "befor": 31, "approach": 31, "abil": 31, "itself": [31, 36], "upon": 31, "quadrat": 31, "horizont": 31, "coordin": [31, 35], "configur": [31, 45], "ultim": 31, "illustr": 31, "intens": 31, "magnitud": 31, "unknown": 31, "variant": 31, "kept": 31, "pull": 31, "lightdarkdomain": 31, "repo": 31, "lightdarkenviron": [31, 34], "const": [31, 34, 35], "lightdarkviz": [31, 34], "log_posit": [31, 34], "set_goal": [31, 34], "set_initial_belief_po": [31, 34], "noise_covari": [31, 35], "func": [31, 35], "jac_dx": [31, 35], "func_nois": [31, 35], "jac_du": [31, 35], "subseteq": 33, "veloc": 33, "x_t": [33, 35], "x_rang": 34, "y_rang": 34, "goal_po": 34, "m_0": 34, "path_color": 34, "254": 34, "path_styl": 34, "path_width": 34, "ident": 35, "zero": [14, 35, 37], "omegasimmathc": 35, "rac": 35, "s_x": 35, "ext": 35, "notat": 35, "element": 35, "fig": 35, "u_t": 35, "xt": [35, 45], "jacobian": 35, "respect": 35, "var_sysd": 35, "distinguish": 36, "perceiv": [36, 37], "tell": 36, "statu": 36, "ob": 36, "extrem": [36, 57], "dumb": [36, 57], "load_unload_problem": 36, "presenc": 37, "absenc": 37, "wall": [37, 38], "squar": 37, "non": 37, "slip": 37, "attempt": [14, 37], "had": 37, "consequ": 37, "positit": 38, "mazeenviron": 39, "scheme": [42, 44], "robot_id": [42, 43, 44, 45, 46, 47], "belief_rep": [42, 43], "agent_has_map": 42, "cours": 42, "scenario": 42, "past": 42, "give": 42, "next_robot_st": [42, 46], "max_tim": [42, 50], "120": [42, 50], "max_step": [42, 50], "findact": [42, 44], "width": [42, 43, 46, 47, 50, 53, 55], "length": [42, 43, 46, 47, 50, 53, 55], "num_obj": 42, "num_obstacl": 42, "robot_char": 42, "mosenviron": [42, 45], "interpret_robot_id": [42, 45], "object_color": [42, 45], "mosviz": [42, 45, 53], "img_width": [42, 45, 50, 53], "img_height": [42, 45, 50, 53], "last_observ": [42, 45, 50, 53], "draw_robot": [42, 45, 50, 53], "draw_observ": [42, 45, 50, 53], "draw_belief": [42, 45, 50, 53], "on_init": [42, 45, 50, 53], "on_ev": [42, 45, 50, 53], "on_loop": [42, 45, 50, 53], "on_rend": [42, 45, 50, 53], "on_cleanup": [42, 45, 50, 53], "on_execut": [42, 45, 50, 53], "render_env": [42, 45, 50, 53], "motionact": [42, 44, 47], "scheme_xyth": [42, 44], "east": [42, 44, 48, 49], "west": [42, 44, 48, 49], "south": [42, 44, 48, 49], "scheme_vw": [42, 44], "forward": [42, 44], "backward": [14, 42, 44], "scheme_xi": [42, 44], "east2d": [42, 44, 55], "west2d": [42, 44, 55], "north2d": [42, 44, 55], "south2d": [42, 44, 55], "lookact": [42, 44], "objectobserv": [42, 44, 46], "null": [42, 44, 46], "for_obj": [42, 44], "robotst": [42, 44], "robot_pos": [42, 44, 47], "objects_found": [42, 44], "mosoost": [42, 44], "object_pos": [42, 44], "mosobservationmodel": [42, 46], "objectobservationmodel": [42, 46], "mosrewardmodel": [42, 46], "goalrewardmodel": [42, 46], "mostransitionmodel": [42, 46], "staticobjecttransitionmodel": [42, 46], "robottransitionmodel": [42, 46], "if_move_bi": [42, 46, 50, 54], "valid_pos": [42, 46, 50, 54, 55], "in_boundari": [42, 46], "mosag": 43, "init_robot_st": 43, "object_id": [43, 46], "dim": [43, 45, 46], "clear_histori": [43, 50, 51], "custum": [43, 51], "mosoobelief": 43, "initialize_belief": [43, 50, 51], "robot_orient": 43, "unspecifi": 43, "radian": 43, "45deg": 44, "forc": 44, "everi": [44, 48, 49], "drop": 44, "distance_cost": 44, "motion_nam": 44, "141592653589793": 44, "71238898038469": 44, "5707963267948966": 44, "vw": 44, "7853981633974483": 44, "objpos": 44, "s_1": 44, "s_2": 44, "s_n": 44, "s_r": 44, "leq": 44, "sr": 44, "objclass": 44, "camera_direct": 44, "overrid": 45, "worldstr": [45, 50, 53, 55], "rx": [45, 53], "fov": [45, 47], "90": [45, 47], "min_rang": [45, 47], "max_rang": [45, 47], "obsticl": 45, "replac": 45, "upper": 45, "letter": 45, "serv": 45, "signal": 45, "laser2dsensor": [45, 47], "robot_nam": 45, "worldmap": 45, "angle_incr": [45, 47], "dist_rang": 45, "angular": 45, "distanc": [45, 47], "measur": 45, "rad": 45, "proxim": [45, 47], "occlusion_en": [45, 47], "fp": [45, 53], "viz_observ": 45, "img": [45, 53], "ry": [45, 53], "rth": [45, 53], "target_color": [45, 53], "init": [45, 53], "event": [45, 53], "display_surf": [45, 53], "occup": [46, 51], "target_object": 46, "big": [46, 50, 51, 53, 54], "detect": 46, "necessarili": 46, "next_object_st": 46, "check_collis": 46, "robot_st": 46, "pose_objid": 46, "overlap": 46, "assist": 47, "collis": 47, "gridmap": [47, 50, 51, 54, 55], "valid_mot": [47, 50, 54, 55], "all_motion_act": 47, "bump": [14, 47], "assumpt": 47, "to_rad": 47, "deg": 47, "in_rang": 47, "val": 47, "env_stat": 47, "within_rang": 47, "visibl": [14, 47], "gap": 47, "sensing_region_s": 47, "in_field_of_view": 47, "view_angl": 47, "field": [14, 47, 56, 57], "view": [14, 47], "180": 47, "270": 47, "shoot_beam": 47, "shoot": 47, "bear": 47, "valid_beam": 47, "dist": 47, "increment": 47, "mosobserv": 47, "proximitysensor": 47, "k": [48, 49], "uai": [48, 49], "rocktype_1": [48, 49], "rocktype_2": [48, 49], "rocktype_k": [48, 49], "rocktype_i": [48, 49], "terminalst": [48, 49], "rock": [48, 49], "check_i": [48, 49], "smartli": [48, 49], "check_1": [48, 49], "check_k": [48, 49], "four": [48, 49], "noisi": [48, 49], "eta": [48, 49], "exit": [48, 49], "area": [48, 49], "being": [48, 49], "invert": [48, 49], "rock_id": [48, 49], "qualiti": [48, 49], "rock_loc": 48, "in_exit_area": [48, 49], "half_efficiency_dist": 48, "random_free_loc": [48, 49], "not_free_loc": [48, 49], "nxn": [48, 49], "generate_inst": [48, 49], "print_stat": [48, 49], "rsaction": [48, 49], "rsobserv": [48, 49], "rsstate": [48, 49], "run_rocksampl": 48, "regular": 50, "initialize_particles_belief": [50, 51], "tagag": [50, 51], "tagact": [50, 52], "tagobserv": [50, 52], "tagstat": [50, 52], "tagenviron": [50, 53], "from_str": [50, 53, 54, 55], "tagviz": [50, 53], "free_cel": [50, 54, 55], "motion_polici": [50, 54], "tagtargetmotionpolici": [50, 54, 55], "tagobservationmodel": [50, 54], "tagpolicymodel": [50, 54], "tagrewardmodel": [50, 54], "tagtransitionmodel": [50, 54], "init_robot_posit": [50, 51], "init_target_posit": 50, "pr_stai": [50, 51, 53, 55], "belief_typ": 50, "hist": 50, "planner_typ": 50, "target_posit": [52, 55], "person": 52, "robot_posit": [52, 55], "target_found": 52, "ohterwis": 54, "anyth": 54, "stochaist": 54, "movement": 54, "closer": 54, "target_motion_polici": 54, "obstacle_pos": 55, "all_mot": 55, "next_target_posit": 55, "valid_target_motion_act": 55, "run_tig": 56, "tigerobservationmodel": [56, 57], "tigerpolicymodel": [56, 57], "tigerrewardmodel": [56, 57], "tigertransitionmodel": [56, 57], "build_act": [56, 57], "build_observ": [56, 57], "build_set": [56, 57], "build_stat": [56, 57], "fact": 56, "debug_tre": 56, "obs_prob": 57, "trans_prob": 57, "fix": 14, "cpdef": 14, "cdef": 14, "failur": 14, "29": 14, "comment": 14, "sp": 14, "minor": 14, "bug": 14, "__str__": 14, "confus": 14, "improv": 14, "clarifi": 14, "gave": 14, "cryingbabi": 14, "pygraphviz": 14, "inspect": 14, "refactor": 14, "cli": 14, "simplifi": 14, "__ne__": 14, "reorgan": 14, "break": 14, "unnecessari": 14, "compat": 14, "pickl": 14, "edit": 14, "cimport": 14, "ed": 14, "pypi": 14, "value_funct": 14, "18fc58e0": 14, "cfc88e8d8": 14, "719c2edf5": 14, "docker": 14, "issu": 14, "citat": 14, "resolv": 14, "max": 14, "among": 14, "infin": 14, "thank": 14, "jason": 14, "clarif": 14, "convert": 14, "were": 14, "calcul": 14, "divid": 14, "thrown": 14, "infinit": 14, "anoth": 14, "differenti": 14, "per": 14, "faster": 14, "readi": 14, "changeabl": 14, "rewritten": 14, "cleaner": 14, "wheel": 14, "properli": 14, "tame": 14, "eol": 14}, "objects": {"pomdp_problems": [[30, 0, 0, "-", "lasertag"], [31, 0, 0, "-", "light_dark"], [36, 0, 0, "-", "load_unload"], [37, 0, 0, "-", "maze"], [48, 0, 0, "-", "rocksample"], [50, 0, 0, "-", "tag"]], "pomdp_problems.light_dark": [[32, 0, 0, "-", "agent"], [33, 0, 0, "-", "domain"], [34, 0, 0, "-", "env"], [35, 0, 0, "-", "models"], [31, 0, 0, "-", "problem_discrete"]], "pomdp_problems.light_dark.agent": [[32, 0, 0, "-", "belief"]], "pomdp_problems.light_dark.domain": [[33, 0, 0, "-", "action"], [33, 0, 0, "-", "observation"], [33, 0, 0, "-", "state"]], "pomdp_problems.light_dark.domain.action": [[33, 1, 1, "", "Action"]], "pomdp_problems.light_dark.domain.observation": [[33, 1, 1, "", "Observation"]], "pomdp_problems.light_dark.domain.observation.Observation": [[33, 2, 1, "", "PRECISION"], [33, 3, 1, "", "discretize"]], "pomdp_problems.light_dark.domain.state": [[33, 1, 1, "", "State"]], "pomdp_problems.light_dark.env": [[34, 0, 0, "-", "env"], [34, 0, 0, "-", "visual"]], "pomdp_problems.light_dark.env.env": [[34, 1, 1, "", "LightDarkEnvironment"]], "pomdp_problems.light_dark.env.env.LightDarkEnvironment": [[34, 4, 1, "", "const"], [34, 4, 1, "", "light"]], "pomdp_problems.light_dark.env.visual": [[34, 1, 1, "", "LightDarkViz"]], "pomdp_problems.light_dark.env.visual.LightDarkViz": [[34, 3, 1, "", "log_position"], [34, 3, 1, "", "plot"], [34, 3, 1, "", "set_goal"], [34, 3, 1, "", "set_initial_belief_pos"]], "pomdp_problems.light_dark.models": [[35, 0, 0, "-", "observation_model"], [35, 0, 0, "-", "transition_model"]], "pomdp_problems.light_dark.models.observation_model": [[35, 1, 1, "", "ObservationModel"]], "pomdp_problems.light_dark.models.observation_model.ObservationModel": [[35, 3, 1, "", "argmax"], [35, 3, 1, "", "func"], [35, 3, 1, "", "func_noise"], [35, 3, 1, "", "jac_dx"], [35, 3, 1, "", "noise_covariance"], [35, 3, 1, "", "probability"], [35, 3, 1, "", "sample"]], "pomdp_problems.light_dark.models.transition_model": [[35, 1, 1, "", "TransitionModel"]], "pomdp_problems.light_dark.models.transition_model.TransitionModel": [[35, 3, 1, "", "argmax"], [35, 3, 1, "", "func"], [35, 3, 1, "", "func_noise"], [35, 3, 1, "", "jac_du"], [35, 3, 1, "", "jac_dx"], [35, 3, 1, "", "probability"], [35, 3, 1, "", "sample"]], "pomdp_problems.light_dark.problem_discrete": [[31, 1, 1, "", "DiscreteLightDark"]], "pomdp_problems.load_unload": [[36, 0, 0, "-", "load_unload"]], "pomdp_problems.load_unload.load_unload": [[36, 1, 1, "", "LUAction"], [36, 1, 1, "", "LUObservation"], [36, 1, 1, "", "LUObservationModel"], [36, 1, 1, "", "LUPolicyModel"], [36, 1, 1, "", "LURewardModel"], [36, 1, 1, "", "LUState"], [36, 1, 1, "", "LUTransitionModel"], [36, 1, 1, "", "LoadUnloadProblem"], [36, 5, 1, "", "generate_init_belief"], [36, 5, 1, "", "generate_random_state"], [36, 5, 1, "", "main"], [36, 5, 1, "", "test_planner"]], "pomdp_problems.load_unload.load_unload.LUObservationModel": [[36, 3, 1, "", "argmax"], [36, 3, 1, "", "probability"], [36, 3, 1, "", "sample"]], "pomdp_problems.load_unload.load_unload.LUPolicyModel": [[36, 3, 1, "", "argmax"], [36, 3, 1, "", "get_all_actions"], [36, 3, 1, "", "probability"], [36, 3, 1, "", "sample"]], "pomdp_problems.load_unload.load_unload.LURewardModel": [[36, 3, 1, "", "argmax"], [36, 3, 1, "", "probability"], [36, 3, 1, "", "sample"]], "pomdp_problems.load_unload.load_unload.LUTransitionModel": [[36, 3, 1, "", "argmax"], [36, 3, 1, "", "probability"], [36, 3, 1, "", "sample"]], "pomdp_problems.maze": [[38, 0, 0, "-", "domain"], [39, 0, 0, "-", "env"], [40, 0, 0, "-", "models"]], "pomdp_problems.maze.domain": [[38, 0, 0, "-", "action"], [38, 0, 0, "-", "observation"], [38, 0, 0, "-", "state"]], "pomdp_problems.maze.domain.observation": [[38, 1, 1, "", "Observation"]], "pomdp_problems.maze.domain.state": [[38, 1, 1, "", "State"]], "pomdp_problems.maze.env": [[39, 0, 0, "-", "env"]], "pomdp_problems.maze.env.env": [[39, 1, 1, "", "MazeEnvironment"]], "pomdp_problems.maze.models": [[41, 0, 0, "-", "components"]], "pomdp_problems.multi_object_search.agent": [[43, 0, 0, "-", "agent"], [43, 0, 0, "-", "belief"]], "pomdp_problems.multi_object_search.agent.agent": [[43, 1, 1, "", "MosAgent"]], "pomdp_problems.multi_object_search.agent.agent.MosAgent": [[43, 3, 1, "", "clear_history"]], "pomdp_problems.multi_object_search.agent.belief": [[43, 1, 1, "", "MosOOBelief"], [43, 5, 1, "", "initialize_belief"]], "pomdp_problems.multi_object_search.agent.belief.MosOOBelief": [[43, 3, 1, "", "mpe"], [43, 3, 1, "", "random"]], "pomdp_problems.multi_object_search.domain": [[44, 0, 0, "-", "action"], [44, 0, 0, "-", "observation"], [44, 0, 0, "-", "state"]], "pomdp_problems.multi_object_search.domain.action": [[44, 1, 1, "", "Action"], [44, 1, 1, "", "FindAction"], [44, 1, 1, "", "LookAction"], [44, 1, 1, "", "MotionAction"]], "pomdp_problems.multi_object_search.domain.action.MotionAction": [[44, 2, 1, "", "BACKWARD"], [44, 2, 1, "", "EAST"], [44, 2, 1, "", "EAST2D"], [44, 2, 1, "", "FORWARD"], [44, 2, 1, "", "LEFT"], [44, 2, 1, "", "NORTH"], [44, 2, 1, "", "NORTH2D"], [44, 2, 1, "", "RIGHT"], [44, 2, 1, "", "SCHEMES"], [44, 2, 1, "", "SCHEME_VW"], [44, 2, 1, "", "SCHEME_XY"], [44, 2, 1, "", "SCHEME_XYTH"], [44, 2, 1, "", "SOUTH"], [44, 2, 1, "", "SOUTH2D"], [44, 2, 1, "", "WEST"], [44, 2, 1, "", "WEST2D"]], "pomdp_problems.multi_object_search.domain.observation": [[44, 1, 1, "", "MosOOObservation"], [44, 1, 1, "", "ObjectObservation"]], "pomdp_problems.multi_object_search.domain.observation.MosOOObservation": [[44, 3, 1, "", "factor"], [44, 3, 1, "", "for_obj"], [44, 3, 1, "", "merge"]], "pomdp_problems.multi_object_search.domain.observation.ObjectObservation": [[44, 2, 1, "", "NULL"]], "pomdp_problems.multi_object_search.domain.state": [[44, 1, 1, "", "MosOOState"], [44, 1, 1, "", "ObjectState"], [44, 1, 1, "", "RobotState"]], "pomdp_problems.multi_object_search.domain.state.MosOOState": [[44, 3, 1, "", "object_pose"], [44, 4, 1, "", "object_poses"], [44, 3, 1, "", "pose"]], "pomdp_problems.multi_object_search.domain.state.ObjectState": [[44, 4, 1, "", "objid"], [44, 4, 1, "", "pose"]], "pomdp_problems.multi_object_search.domain.state.RobotState": [[44, 4, 1, "", "objects_found"], [44, 4, 1, "", "pose"], [44, 4, 1, "", "robot_pose"]], "pomdp_problems.multi_object_search.env": [[45, 0, 0, "-", "env"], [45, 0, 0, "-", "visual"]], "pomdp_problems.multi_object_search.env.env": [[45, 1, 1, "", "MosEnvironment"], [45, 5, 1, "", "equip_sensors"], [45, 5, 1, "", "interpret"], [45, 5, 1, "", "interpret_robot_id"], [45, 5, 1, "", "make_laser_sensor"], [45, 5, 1, "", "make_proximity_sensor"]], "pomdp_problems.multi_object_search.env.env.MosEnvironment": [[45, 4, 1, "", "robot_ids"], [45, 3, 1, "", "state_transition"]], "pomdp_problems.multi_object_search.env.visual": [[45, 1, 1, "", "MosViz"], [45, 5, 1, "", "object_color"], [45, 5, 1, "", "unittest"]], "pomdp_problems.multi_object_search.env.visual.MosViz": [[45, 3, 1, "", "draw_belief"], [45, 3, 1, "", "draw_observation"], [45, 3, 1, "", "draw_robot"], [45, 4, 1, "", "img_height"], [45, 4, 1, "", "img_width"], [45, 4, 1, "", "last_observation"], [45, 3, 1, "", "on_cleanup"], [45, 3, 1, "", "on_event"], [45, 3, 1, "", "on_execute"], [45, 3, 1, "", "on_init"], [45, 3, 1, "", "on_loop"], [45, 3, 1, "", "on_render"], [45, 3, 1, "", "render_env"], [45, 3, 1, "", "update"]], "pomdp_problems.multi_object_search": [[42, 0, 0, "-", "example_worlds"], [42, 0, 0, "-", "problem"]], "pomdp_problems.multi_object_search.example_worlds": [[42, 5, 1, "", "random_world"]], "pomdp_problems.multi_object_search.models": [[47, 0, 0, "-", "components"], [46, 0, 0, "-", "observation_model"], [46, 0, 0, "-", "policy_model"], [46, 0, 0, "-", "reward_model"], [46, 0, 0, "-", "transition_model"]], "pomdp_problems.multi_object_search.models.components": [[47, 0, 0, "-", "grid_map"], [47, 0, 0, "-", "sensor"]], "pomdp_problems.multi_object_search.models.components.grid_map": [[47, 1, 1, "", "GridMap"]], "pomdp_problems.multi_object_search.models.components.grid_map.GridMap": [[47, 3, 1, "", "valid_motions"]], "pomdp_problems.multi_object_search.models.components.sensor": [[47, 1, 1, "", "Laser2DSensor"], [47, 1, 1, "", "ProximitySensor"], [47, 1, 1, "", "Sensor"], [47, 5, 1, "", "euclidean_dist"], [47, 5, 1, "", "in_range"], [47, 5, 1, "", "to_rad"]], "pomdp_problems.multi_object_search.models.components.sensor.Laser2DSensor": [[47, 3, 1, "", "in_field_of_view"], [47, 3, 1, "", "observe"], [47, 4, 1, "", "sensing_region_size"], [47, 3, 1, "", "shoot_beam"], [47, 3, 1, "", "valid_beam"], [47, 3, 1, "", "within_range"]], "pomdp_problems.multi_object_search.models.components.sensor.Sensor": [[47, 2, 1, "", "LASER"], [47, 2, 1, "", "PROXIMITY"], [47, 3, 1, "", "observe"], [47, 4, 1, "", "robot_id"], [47, 4, 1, "", "sensing_region_size"], [47, 3, 1, "", "within_range"]], "pomdp_problems.multi_object_search.models.observation_model": [[46, 1, 1, "", "MosObservationModel"], [46, 1, 1, "", "ObjectObservationModel"], [46, 5, 1, "", "unittest"]], "pomdp_problems.multi_object_search.models.observation_model.MosObservationModel": [[46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.models.observation_model.ObjectObservationModel": [[46, 3, 1, "", "argmax"], [46, 3, 1, "", "probability"], [46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.models.policy_model": [[46, 1, 1, "", "PolicyModel"]], "pomdp_problems.multi_object_search.models.policy_model.PolicyModel": [[46, 3, 1, "", "argmax"], [46, 3, 1, "", "get_all_actions"], [46, 3, 1, "", "probability"], [46, 3, 1, "", "rollout"], [46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.models.reward_model": [[46, 1, 1, "", "GoalRewardModel"], [46, 1, 1, "", "MosRewardModel"]], "pomdp_problems.multi_object_search.models.reward_model.MosRewardModel": [[46, 3, 1, "", "argmax"], [46, 3, 1, "", "probability"], [46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.models.transition_model": [[46, 1, 1, "", "MosTransitionModel"], [46, 1, 1, "", "RobotTransitionModel"], [46, 1, 1, "", "StaticObjectTransitionModel"], [46, 5, 1, "", "in_boundary"], [46, 5, 1, "", "valid_pose"]], "pomdp_problems.multi_object_search.models.transition_model.MosTransitionModel": [[46, 3, 1, "", "argmax"], [46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.models.transition_model.RobotTransitionModel": [[46, 3, 1, "", "argmax"], [46, 3, 1, "", "if_move_by"], [46, 3, 1, "", "probability"], [46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.models.transition_model.StaticObjectTransitionModel": [[46, 3, 1, "", "argmax"], [46, 3, 1, "", "probability"], [46, 3, 1, "", "sample"]], "pomdp_problems.multi_object_search.problem": [[42, 1, 1, "", "MosOOPOMDP"], [42, 5, 1, "", "belief_update"], [42, 5, 1, "", "solve"], [42, 5, 1, "", "unittest"]], "pomdp_problems.rocksample": [[49, 0, 0, "-", "cythonize"], [48, 0, 0, "module-0", "rocksample_problem"]], "pomdp_problems.rocksample.cythonize": [[49, 0, 0, "-", "rocksample_problem"]], "pomdp_problems.rocksample.cythonize.rocksample_problem": [[49, 1, 1, "", "CheckAction"], [49, 1, 1, "", "MoveAction"], [49, 1, 1, "", "RSAction"], [49, 1, 1, "", "RSObservation"], [49, 1, 1, "", "RSObservationModel"], [49, 1, 1, "", "RSPolicyModel"], [49, 1, 1, "", "RSRewardModel"], [49, 1, 1, "", "RSState"], [49, 1, 1, "", "RSTransitionModel"], [49, 1, 1, "", "RockSampleProblem"], [49, 1, 1, "", "RockType"], [49, 1, 1, "", "SampleAction"], [49, 5, 1, "", "euclidean_dist"], [49, 5, 1, "", "init_particles_belief"], [49, 5, 1, "", "main"], [49, 5, 1, "", "test_planner"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.CheckAction": [[49, 2, 1, "", "rock_id"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction": [[49, 2, 1, "", "EAST"], [49, 2, 1, "", "NORTH"], [49, 2, 1, "", "SOUTH"], [49, 2, 1, "", "WEST"], [49, 2, 1, "", "motion"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservation": [[49, 2, 1, "", "quality"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservationModel": [[49, 3, 1, "", "argmax"], [49, 3, 1, "", "probability"], [49, 3, 1, "", "sample"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel": [[49, 3, 1, "", "argmax"], [49, 3, 1, "", "get_all_actions"], [49, 3, 1, "", "probability"], [49, 3, 1, "", "rollout"], [49, 3, 1, "", "sample"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RSRewardModel": [[49, 3, 1, "", "argmax"], [49, 3, 1, "", "probability"], [49, 3, 1, "", "sample"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RSState": [[49, 2, 1, "", "position"], [49, 2, 1, "", "rocktypes"], [49, 2, 1, "", "terminal"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RSTransitionModel": [[49, 3, 1, "", "argmax"], [49, 3, 1, "", "probability"], [49, 3, 1, "", "sample"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RockSampleProblem": [[49, 3, 1, "", "generate_instance"], [49, 3, 1, "", "in_exit_area"], [49, 3, 1, "", "print_state"], [49, 3, 1, "", "random_free_location"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.RockType": [[49, 2, 1, "", "BAD"], [49, 2, 1, "", "GOOD"], [49, 3, 1, "", "invert"], [49, 3, 1, "", "random"]], "pomdp_problems.rocksample.rocksample_problem": [[48, 1, 1, "id8", "Action"], [48, 1, 1, "id15", "CheckAction"], [48, 1, 1, "id9", "MoveAction"], [48, 1, 1, "id16", "Observation"], [48, 1, 1, "id21", "RSObservationModel"], [48, 1, 1, "id29", "RSPolicyModel"], [48, 1, 1, "id25", "RSRewardModel"], [48, 1, 1, "id17", "RSTransitionModel"], [48, 1, 1, "id35", "RockSampleProblem"], [48, 1, 1, "id2", "RockType"], [48, 1, 1, "id14", "SampleAction"], [48, 1, 1, "id7", "State"], [48, 5, 1, "id0", "euclidean_dist"], [48, 5, 1, "id41", "init_particles_belief"], [48, 5, 1, "id42", "main"], [48, 5, 1, "id40", "test_planner"]], "pomdp_problems.rocksample.rocksample_problem.MoveAction": [[48, 2, 1, "id10", "EAST"], [48, 2, 1, "id12", "NORTH"], [48, 2, 1, "id13", "SOUTH"], [48, 2, 1, "id11", "WEST"]], "pomdp_problems.rocksample.rocksample_problem.RSObservationModel": [[48, 3, 1, "id24", "argmax"], [48, 3, 1, "id22", "probability"], [48, 3, 1, "id23", "sample"]], "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel": [[48, 3, 1, "id32", "argmax"], [48, 3, 1, "id33", "get_all_actions"], [48, 3, 1, "id31", "probability"], [48, 3, 1, "id34", "rollout"], [48, 3, 1, "id30", "sample"]], "pomdp_problems.rocksample.rocksample_problem.RSRewardModel": [[48, 3, 1, "id27", "argmax"], [48, 3, 1, "id28", "probability"], [48, 3, 1, "id26", "sample"]], "pomdp_problems.rocksample.rocksample_problem.RSTransitionModel": [[48, 3, 1, "id20", "argmax"], [48, 3, 1, "id18", "probability"], [48, 3, 1, "id19", "sample"]], "pomdp_problems.rocksample.rocksample_problem.RockSampleProblem": [[48, 3, 1, "id38", "generate_instance"], [48, 3, 1, "id37", "in_exit_area"], [48, 3, 1, "id39", "print_state"], [48, 3, 1, "id36", "random_free_location"]], "pomdp_problems.rocksample.rocksample_problem.RockType": [[48, 2, 1, "id4", "BAD"], [48, 2, 1, "id3", "GOOD"], [48, 3, 1, "id5", "invert"], [48, 3, 1, "id6", "random"]], "pomdp_problems.tag": [[51, 0, 0, "-", "agent"], [50, 0, 0, "-", "constants"], [52, 0, 0, "-", "domain"], [53, 0, 0, "-", "env"], [50, 0, 0, "-", "example_worlds"], [50, 0, 0, "-", "experiment"], [54, 0, 0, "-", "models"], [50, 0, 0, "-", "problem"]], "pomdp_problems.tag.agent": [[51, 0, 0, "-", "agent"]], "pomdp_problems.tag.agent.agent": [[51, 1, 1, "", "TagAgent"], [51, 5, 1, "", "belief_update"], [51, 5, 1, "", "initialize_belief"], [51, 5, 1, "", "initialize_particles_belief"]], "pomdp_problems.tag.agent.agent.TagAgent": [[51, 3, 1, "", "clear_history"]], "pomdp_problems.tag.domain": [[52, 0, 0, "-", "action"], [52, 0, 0, "-", "observation"], [52, 0, 0, "-", "state"]], "pomdp_problems.tag.domain.action": [[52, 1, 1, "", "TagAction"]], "pomdp_problems.tag.domain.observation": [[52, 1, 1, "", "TagObservation"]], "pomdp_problems.tag.domain.state": [[52, 1, 1, "", "TagState"]], "pomdp_problems.tag.env": [[53, 0, 0, "-", "env"], [53, 0, 0, "-", "visual"]], "pomdp_problems.tag.env.env": [[53, 1, 1, "", "TagEnvironment"]], "pomdp_problems.tag.env.env.TagEnvironment": [[53, 3, 1, "", "from_str"], [53, 4, 1, "", "grid_map"], [53, 4, 1, "", "length"], [53, 4, 1, "", "width"]], "pomdp_problems.tag.env.visual": [[53, 1, 1, "", "TagViz"], [53, 5, 1, "", "unittest"]], "pomdp_problems.tag.env.visual.TagViz": [[53, 3, 1, "", "draw_belief"], [53, 3, 1, "", "draw_observation"], [53, 3, 1, "", "draw_robot"], [53, 4, 1, "", "img_height"], [53, 4, 1, "", "img_width"], [53, 4, 1, "", "last_observation"], [53, 3, 1, "", "on_cleanup"], [53, 3, 1, "", "on_event"], [53, 3, 1, "", "on_execute"], [53, 3, 1, "", "on_init"], [53, 3, 1, "", "on_loop"], [53, 3, 1, "", "on_render"], [53, 3, 1, "", "render_env"], [53, 3, 1, "", "update"]], "pomdp_problems.tag.experiment": [[50, 5, 1, "", "main"], [50, 5, 1, "", "trial"]], "pomdp_problems.tag.models": [[55, 0, 0, "-", "components"], [54, 0, 0, "-", "observation_model"], [54, 0, 0, "-", "policy_model"], [54, 0, 0, "-", "reward_model"], [54, 0, 0, "-", "transition_model"]], "pomdp_problems.tag.models.components": [[55, 0, 0, "-", "grid_map"], [55, 0, 0, "-", "motion_policy"]], "pomdp_problems.tag.models.components.grid_map": [[55, 1, 1, "", "GridMap"]], "pomdp_problems.tag.models.components.grid_map.GridMap": [[55, 3, 1, "", "free_cells"], [55, 3, 1, "", "from_str"], [55, 3, 1, "", "valid_motions"], [55, 3, 1, "", "valid_pose"]], "pomdp_problems.tag.models.components.motion_policy": [[55, 1, 1, "", "TagTargetMotionPolicy"]], "pomdp_problems.tag.models.components.motion_policy.TagTargetMotionPolicy": [[55, 3, 1, "", "mpe"], [55, 3, 1, "", "probability"], [55, 3, 1, "", "random"]], "pomdp_problems.tag.models.observation_model": [[54, 1, 1, "", "TagObservationModel"]], "pomdp_problems.tag.models.observation_model.TagObservationModel": [[54, 3, 1, "", "argmax"], [54, 3, 1, "", "probability"], [54, 3, 1, "", "sample"]], "pomdp_problems.tag.models.policy_model": [[54, 1, 1, "", "TagPolicyModel"]], "pomdp_problems.tag.models.policy_model.TagPolicyModel": [[54, 3, 1, "", "get_all_actions"], [54, 3, 1, "", "rollout"], [54, 3, 1, "", "sample"]], "pomdp_problems.tag.models.reward_model": [[54, 1, 1, "", "TagRewardModel"]], "pomdp_problems.tag.models.reward_model.TagRewardModel": [[54, 3, 1, "", "probability"], [54, 3, 1, "", "sample"]], "pomdp_problems.tag.models.transition_model": [[54, 1, 1, "", "TagTransitionModel"]], "pomdp_problems.tag.models.transition_model.TagTransitionModel": [[54, 3, 1, "", "argmax"], [54, 3, 1, "", "if_move_by"], [54, 3, 1, "", "probability"], [54, 3, 1, "", "sample"]], "pomdp_problems.tag.problem": [[50, 1, 1, "", "TagProblem"], [50, 5, 1, "", "main"], [50, 5, 1, "", "solve"]], "pomdp_problems.tiger": [[57, 0, 0, "-", "cythonize"], [56, 0, 0, "-", "tiger_problem"]], "pomdp_problems.tiger.cythonize": [[57, 0, 0, "-", "tiger_problem"]], "pomdp_problems.tiger.cythonize.tiger_problem": [[57, 1, 1, "", "TigerAction"], [57, 1, 1, "", "TigerObservation"], [57, 1, 1, "", "TigerObservationModel"], [57, 1, 1, "", "TigerPolicyModel"], [57, 1, 1, "", "TigerProblem"], [57, 1, 1, "", "TigerRewardModel"], [57, 1, 1, "", "TigerState"], [57, 1, 1, "", "TigerTransitionModel"], [57, 5, 1, "", "build_actions"], [57, 5, 1, "", "build_observations"], [57, 5, 1, "", "build_setting"], [57, 5, 1, "", "build_states"], [57, 5, 1, "", "main"], [57, 5, 1, "", "test_planner"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservation": [[57, 2, 1, "", "name"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel": [[57, 3, 1, "", "argmax"], [57, 3, 1, "", "get_all_observations"], [57, 3, 1, "", "get_distribution"], [57, 3, 1, "", "probability"], [57, 3, 1, "", "sample"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerPolicyModel": [[57, 3, 1, "", "argmax"], [57, 3, 1, "", "get_all_actions"], [57, 3, 1, "", "probability"], [57, 3, 1, "", "sample"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerProblem": [[57, 2, 1, "", "ACTIONS"], [57, 2, 1, "", "OBSERVATIONS"], [57, 2, 1, "", "STATES"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerRewardModel": [[57, 3, 1, "", "argmax"], [57, 3, 1, "", "get_distribution"], [57, 3, 1, "", "probability"], [57, 3, 1, "", "sample"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerState": [[57, 2, 1, "", "name"]], "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel": [[57, 3, 1, "", "argmax"], [57, 3, 1, "", "get_all_states"], [57, 3, 1, "", "get_distribution"], [57, 3, 1, "", "probability"], [57, 3, 1, "", "sample"]], "pomdp_problems.tiger.tiger_problem": [[56, 1, 1, "", "ObservationModel"], [56, 1, 1, "", "PolicyModel"], [56, 1, 1, "", "RewardModel"], [56, 1, 1, "", "TigerAction"], [56, 1, 1, "", "TigerObservation"], [56, 1, 1, "", "TigerProblem"], [56, 1, 1, "", "TigerState"], [56, 1, 1, "", "TransitionModel"], [56, 5, 1, "", "main"], [56, 5, 1, "", "test_planner"]], "pomdp_problems.tiger.tiger_problem.ObservationModel": [[56, 3, 1, "", "get_all_observations"], [56, 3, 1, "", "probability"], [56, 3, 1, "", "sample"]], "pomdp_problems.tiger.tiger_problem.PolicyModel": [[56, 2, 1, "", "ACTIONS"], [56, 3, 1, "", "get_all_actions"], [56, 3, 1, "", "rollout"], [56, 3, 1, "", "sample"]], "pomdp_problems.tiger.tiger_problem.RewardModel": [[56, 3, 1, "", "sample"]], "pomdp_problems.tiger.tiger_problem.TigerProblem": [[56, 3, 1, "", "create"]], "pomdp_problems.tiger.tiger_problem.TigerState": [[56, 3, 1, "", "other"]], "pomdp_problems.tiger.tiger_problem.TransitionModel": [[56, 3, 1, "", "get_all_states"], [56, 3, 1, "", "probability"], [56, 3, 1, "", "sample"]], "pomdp_py.algorithms": [[3, 0, 0, "-", "bsp"], [2, 0, 0, "-", "po_rollout"], [2, 0, 0, "-", "po_uct"], [2, 0, 0, "-", "pomcp"], [2, 0, 0, "-", "value_iteration"]], "pomdp_py.algorithms.bsp": [[2, 0, 0, "-", "blqr"]], "pomdp_py.algorithms.bsp.blqr": [[2, 1, 1, "", "BLQR"]], "pomdp_py.algorithms.bsp.blqr.BLQR": [[2, 3, 1, "", "create_plan"], [2, 3, 1, "", "ekf_update_mlo"], [2, 3, 1, "", "integrate_belief_segment"], [2, 3, 1, "", "interpret_sqp_plan"], [2, 3, 1, "", "segmented_cost_function"]], "pomdp_py.algorithms.po_rollout": [[2, 1, 1, "", "PORollout"]], "pomdp_py.algorithms.po_rollout.PORollout": [[2, 3, 1, "", "clear_agent"], [2, 2, 1, "", "last_best_reward"], [2, 3, 1, "", "plan"], [2, 3, 1, "", "set_rollout_policy"], [2, 3, 1, "", "update"], [2, 2, 1, "", "update_agent_belief"]], "pomdp_py.algorithms.po_uct": [[2, 1, 1, "", "ActionPrior"], [2, 1, 1, "", "POUCT"], [2, 1, 1, "", "QNode"], [2, 1, 1, "", "RandomRollout"], [2, 1, 1, "", "RolloutPolicy"], [2, 1, 1, "", "RootVNode"], [2, 1, 1, "", "TreeNode"], [2, 1, 1, "", "VNode"]], "pomdp_py.algorithms.po_uct.ActionPrior": [[2, 3, 1, "", "get_preferred_actions"]], "pomdp_py.algorithms.po_uct.POUCT": [[2, 3, 1, "", "clear_agent"], [2, 2, 1, "", "last_num_sims"], [2, 2, 1, "", "last_planning_time"], [2, 3, 1, "", "plan"], [2, 3, 1, "", "set_rollout_policy"], [2, 3, 1, "", "update"], [2, 2, 1, "", "updates_agent_belief"]], "pomdp_py.algorithms.po_uct.RandomRollout": [[2, 3, 1, "", "rollout"]], "pomdp_py.algorithms.po_uct.RolloutPolicy": [[2, 3, 1, "", "rollout"]], "pomdp_py.algorithms.po_uct.RootVNode": [[2, 3, 1, "", "from_vnode"], [2, 2, 1, "", "history"]], "pomdp_py.algorithms.po_uct.TreeNode": [[2, 2, 1, "", "children"], [2, 2, 1, "", "num_visits"], [2, 2, 1, "", "value"]], "pomdp_py.algorithms.po_uct.VNode": [[2, 3, 1, "", "argmax"], [2, 3, 1, "", "print_children_value"], [2, 2, 1, "", "value"]], "pomdp_py.algorithms.pomcp": [[2, 1, 1, "", "POMCP"], [2, 1, 1, "", "RootVNodeParticles"], [2, 1, 1, "", "VNodeParticles"]], "pomdp_py.algorithms.pomcp.POMCP": [[2, 3, 1, "", "plan"], [2, 3, 1, "", "update"], [2, 2, 1, "", "update_agent_belief"]], "pomdp_py.algorithms.pomcp.RootVNodeParticles": [[2, 2, 1, "", "belief"], [2, 3, 1, "", "from_vnode"]], "pomdp_py.algorithms.pomcp.VNodeParticles": [[2, 2, 1, "", "belief"]], "pomdp_py.algorithms.value_iteration": [[2, 1, 1, "", "ValueIteration"]], "pomdp_py.algorithms.value_iteration.ValueIteration": [[2, 3, 1, "", "plan"]], "pomdp_py.framework": [[5, 0, 0, "-", "basics"], [5, 0, 0, "-", "oopomdp"], [5, 0, 0, "-", "planner"]], "pomdp_py.framework.basics": [[5, 1, 1, "", "Action"], [5, 1, 1, "", "Agent"], [5, 1, 1, "", "BlackboxModel"], [5, 1, 1, "", "Distribution"], [5, 1, 1, "", "Environment"], [5, 1, 1, "", "GenerativeDistribution"], [5, 1, 1, "", "Observation"], [5, 1, 1, "", "ObservationModel"], [5, 1, 1, "", "Option"], [5, 1, 1, "", "POMDP"], [5, 1, 1, "", "PolicyModel"], [5, 1, 1, "", "RewardModel"], [5, 1, 1, "", "State"], [5, 1, 1, "", "TransitionModel"], [5, 5, 1, "", "sample_explict_models"], [5, 5, 1, "", "sample_generative_model"]], "pomdp_py.framework.basics.Agent": [[5, 3, 1, "", "add_attr"], [5, 2, 1, "", "all_actions"], [5, 2, 1, "", "all_observations"], [5, 2, 1, "", "all_states"], [5, 2, 1, "", "belief"], [5, 2, 1, "", "history"], [5, 2, 1, "", "init_belief"], [5, 3, 1, "", "sample_belief"], [5, 3, 1, "", "set_belief"], [5, 3, 1, "", "update"], [5, 3, 1, "", "update_history"]], "pomdp_py.framework.basics.BlackboxModel": [[5, 3, 1, "", "argmax"], [5, 3, 1, "", "sample"]], "pomdp_py.framework.basics.Distribution": [[5, 3, 1, "", "__getitem__"], [5, 3, 1, "", "__setitem__"]], "pomdp_py.framework.basics.Environment": [[5, 3, 1, "", "apply_transition"], [5, 2, 1, "", "blackbox_model"], [5, 2, 1, "", "cur_state"], [5, 3, 1, "", "provide_observation"], [5, 2, 1, "", "reward_model"], [5, 2, 1, "", "state"], [5, 3, 1, "", "state_transition"], [5, 2, 1, "", "transition_model"]], "pomdp_py.framework.basics.GenerativeDistribution": [[5, 3, 1, "", "argmax"], [5, 3, 1, "", "get_histogram"], [5, 3, 1, "", "mpe"]], "pomdp_py.framework.basics.ObservationModel": [[5, 3, 1, "", "argmax"], [5, 3, 1, "", "get_all_observations"], [5, 3, 1, "", "get_distribution"], [5, 3, 1, "", "probability"], [5, 3, 1, "", "sample"]], "pomdp_py.framework.basics.Option": [[5, 3, 1, "", "initiation"], [5, 2, 1, "", "policy"], [5, 3, 1, "", "sample"], [5, 3, 1, "", "termination"]], "pomdp_py.framework.basics.PolicyModel": [[5, 3, 1, "", "argmax"], [5, 3, 1, "", "get_all_actions"], [5, 3, 1, "", "get_distribution"], [5, 3, 1, "", "probability"], [5, 3, 1, "", "sample"], [5, 3, 1, "", "update"]], "pomdp_py.framework.basics.RewardModel": [[5, 3, 1, "", "argmax"], [5, 3, 1, "", "get_distribution"], [5, 3, 1, "", "probability"], [5, 3, 1, "", "sample"]], "pomdp_py.framework.basics.TransitionModel": [[5, 3, 1, "", "argmax"], [5, 3, 1, "", "get_all_states"], [5, 3, 1, "", "get_distribution"], [5, 3, 1, "", "probability"], [5, 3, 1, "", "sample"]], "pomdp_py.framework.oopomdp": [[5, 1, 1, "", "OOBelief"], [5, 1, 1, "", "OOObservation"], [5, 1, 1, "", "OOObservationModel"], [5, 1, 1, "", "OOPOMDP"], [5, 1, 1, "", "OOState"], [5, 1, 1, "", "OOTransitionModel"], [5, 1, 1, "", "ObjectState"]], "pomdp_py.framework.oopomdp.OOBelief": [[5, 3, 1, "", "__getitem__"], [5, 3, 1, "", "__setitem__"], [5, 3, 1, "", "b"], [5, 3, 1, "", "mpe"], [5, 3, 1, "", "object_belief"], [5, 2, 1, "", "object_beliefs"], [5, 3, 1, "", "random"], [5, 3, 1, "", "set_object_belief"]], "pomdp_py.framework.oopomdp.OOObservation": [[5, 3, 1, "", "factor"], [5, 3, 1, "", "merge"]], "pomdp_py.framework.oopomdp.OOObservationModel": [[5, 3, 1, "", "__getitem__"], [5, 3, 1, "", "argmax"], [5, 2, 1, "", "observation_models"], [5, 3, 1, "", "probability"], [5, 3, 1, "", "sample"]], "pomdp_py.framework.oopomdp.OOState": [[5, 3, 1, "", "__getitem__"], [5, 3, 1, "", "copy"], [5, 3, 1, "", "get_object_attribute"], [5, 3, 1, "", "get_object_class"], [5, 3, 1, "", "get_object_state"], [5, 3, 1, "", "s"], [5, 3, 1, "", "set_object_state"], [5, 2, 1, "", "situation"]], "pomdp_py.framework.oopomdp.OOTransitionModel": [[5, 3, 1, "", "__getitem__"], [5, 3, 1, "", "argmax"], [5, 3, 1, "", "probability"], [5, 3, 1, "", "sample"], [5, 2, 1, "", "transition_models"]], "pomdp_py.framework.oopomdp.ObjectState": [[5, 3, 1, "", "__getitem__"], [5, 3, 1, "", "__setitem__"], [5, 3, 1, "", "copy"]], "pomdp_py.framework.planner": [[5, 1, 1, "", "Planner"]], "pomdp_py.framework.planner.Planner": [[5, 3, 1, "", "plan"], [5, 3, 1, "", "update"], [5, 3, 1, "", "updates_agent_belief"]], "pomdp_py.representations.belief": [[7, 0, 0, "-", "histogram"], [7, 0, 0, "-", "particles"]], "pomdp_py.representations.belief.histogram": [[7, 5, 1, "", "abstraction_over_histogram"], [7, 5, 1, "", "update_histogram_belief"]], "pomdp_py.representations.belief.particles": [[7, 5, 1, "", "abstraction_over_particles"], [7, 5, 1, "", "particle_reinvigoration"], [7, 5, 1, "", "update_particles_belief"]], "pomdp_py.representations.distribution": [[8, 0, 0, "-", "gaussian"], [8, 0, 0, "-", "histogram"], [8, 0, 0, "-", "particles"]], "pomdp_py.representations.distribution.gaussian": [[8, 1, 1, "", "Gaussian"]], "pomdp_py.representations.distribution.gaussian.Gaussian": [[8, 3, 1, "", "__getitem__"], [8, 3, 1, "", "__setitem__"], [8, 2, 1, "", "cov"], [8, 2, 1, "", "covariance"], [8, 2, 1, "", "mean"], [8, 3, 1, "", "mpe"], [8, 3, 1, "", "random"], [8, 2, 1, "", "sigma"]], "pomdp_py.representations.distribution.histogram": [[8, 1, 1, "", "Histogram"]], "pomdp_py.representations.distribution.histogram.Histogram": [[8, 3, 1, "", "__getitem__"], [8, 3, 1, "", "__setitem__"], [8, 3, 1, "", "get_histogram"], [8, 2, 1, "", "histogram"], [8, 3, 1, "", "is_normalized"], [8, 3, 1, "", "mpe"], [8, 3, 1, "", "random"]], "pomdp_py.representations.distribution.particles": [[8, 1, 1, "", "Particles"], [8, 1, 1, "", "WeightedParticles"]], "pomdp_py.representations.distribution.particles.Particles": [[8, 3, 1, "", "add"], [8, 3, 1, "", "from_histogram"], [8, 3, 1, "", "get_abstraction"], [8, 3, 1, "", "get_histogram"], [8, 2, 1, "", "particles"], [8, 3, 1, "", "random"]], "pomdp_py.representations.distribution.particles.WeightedParticles": [[8, 3, 1, "", "__getitem__"], [8, 3, 1, "", "__setitem__"], [8, 3, 1, "", "add"], [8, 3, 1, "", "condense"], [8, 3, 1, "", "from_histogram"], [8, 3, 1, "", "get_histogram"], [8, 3, 1, "", "mpe"], [8, 2, 1, "", "particles"], [8, 3, 1, "", "random"], [8, 2, 1, "", "values"], [8, 2, 1, "", "weights"]], "pomdp_py": [[9, 0, 0, "-", "utils"], [12, 0, 0, "-", "visual"]], "pomdp_py.utils": [[9, 0, 0, "-", "colors"], [9, 0, 0, "-", "cython_utils"], [9, 0, 0, "-", "debugging"], [9, 0, 0, "-", "math"], [9, 0, 0, "-", "misc"], [9, 0, 0, "-", "plotting"], [9, 0, 0, "-", "templates"], [9, 0, 0, "-", "test_utils"], [9, 0, 0, "-", "typ"]], "pomdp_py.utils.colors": [[9, 5, 1, "", "hex_to_rgb"], [9, 5, 1, "", "inverse_color_hex"], [9, 5, 1, "", "inverse_color_rgb"], [9, 5, 1, "", "lighter"], [9, 5, 1, "", "random_unique_color"], [9, 5, 1, "", "rgb_to_hex"]], "pomdp_py.utils.cython_utils": [[9, 5, 1, "", "det_dict_hash"]], "pomdp_py.utils.debugging": [[9, 1, 1, "", "TreeDebugger"], [9, 5, 1, "", "interpret_color"], [9, 5, 1, "", "sorted_by_str"]], "pomdp_py.utils.debugging.TreeDebugger": [[9, 4, 1, "", "b"], [9, 3, 1, "", "back"], [9, 4, 1, "", "bestseq"], [9, 3, 1, "", "bestseqd"], [9, 4, 1, "", "c"], [9, 4, 1, "", "clear"], [9, 4, 1, "", "d"], [9, 4, 1, "", "depth"], [9, 3, 1, "", "l"], [9, 3, 1, "", "layer"], [9, 4, 1, "", "leaf"], [9, 3, 1, "", "mark"], [9, 3, 1, "", "mark_path"], [9, 3, 1, "", "mark_sequence"], [9, 3, 1, "", "markp"], [9, 4, 1, "", "mbp"], [9, 4, 1, "", "nl"], [9, 4, 1, "", "nn"], [9, 4, 1, "", "nq"], [9, 4, 1, "", "num_layers"], [9, 3, 1, "", "num_nodes"], [9, 4, 1, "", "nv"], [9, 3, 1, "", "p"], [9, 3, 1, "", "path"], [9, 3, 1, "", "path_to"], [9, 4, 1, "", "pm"], [9, 4, 1, "", "pp"], [9, 3, 1, "", "preferred_actions"], [9, 4, 1, "", "r"], [9, 4, 1, "", "root"], [9, 3, 1, "", "s"], [9, 3, 1, "", "single_node_str"], [9, 3, 1, "", "step"], [9, 3, 1, "", "tree_stats"]], "pomdp_py.utils.interfaces.conversion": [[18, 1, 1, "", "AlphaVectorPolicy"], [18, 1, 1, "", "PolicyGraph"], [18, 5, 1, "", "to_pomdp_file"], [18, 5, 1, "", "to_pomdpx_file"]], "pomdp_py.utils.interfaces.conversion.AlphaVectorPolicy": [[18, 3, 1, "", "construct"], [18, 3, 1, "", "plan"], [18, 3, 1, "", "value"]], "pomdp_py.utils.interfaces.conversion.PolicyGraph": [[18, 3, 1, "", "construct"], [18, 3, 1, "", "plan"], [18, 3, 1, "", "update"]], "pomdp_py.utils.interfaces": [[18, 0, 0, "-", "solvers"]], "pomdp_py.utils.interfaces.solvers": [[18, 5, 1, "", "sarsop"], [18, 5, 1, "", "vi_pruning"]], "pomdp_py.utils.math": [[9, 5, 1, "", "R_between"], [9, 5, 1, "", "R_x"], [9, 5, 1, "", "R_y"], [9, 5, 1, "", "R_z"], [9, 5, 1, "", "T"], [9, 5, 1, "", "approx_equal"], [9, 5, 1, "", "euclidean_dist"], [9, 5, 1, "", "proj"], [9, 5, 1, "", "to_radians"], [9, 5, 1, "", "vec"]], "pomdp_py.utils.misc": [[9, 5, 1, "", "json_safe"], [9, 5, 1, "", "remap"], [9, 5, 1, "", "safe_slice"], [9, 5, 1, "", "similar"], [9, 1, 1, "", "special_char"]], "pomdp_py.utils.misc.special_char": [[9, 2, 1, "", "SUBSCRIPT"], [9, 2, 1, "", "bottomleft"], [9, 2, 1, "", "bottomright"], [9, 2, 1, "", "bottomt"], [9, 2, 1, "", "down"], [9, 2, 1, "", "hline"], [9, 2, 1, "", "intersect"], [9, 2, 1, "", "left"], [9, 2, 1, "", "leftt"], [9, 2, 1, "", "longbottomleft"], [9, 2, 1, "", "longbottomright"], [9, 2, 1, "", "longleft"], [9, 2, 1, "", "longright"], [9, 2, 1, "", "longtopleft"], [9, 2, 1, "", "longtopright"], [9, 2, 1, "", "right"], [9, 2, 1, "", "rightt"], [9, 2, 1, "", "shadebar"], [9, 2, 1, "", "topleft"], [9, 2, 1, "", "topright"], [9, 2, 1, "", "topt"], [9, 2, 1, "", "up"], [9, 2, 1, "", "vline"]], "pomdp_py.utils.plotting": [[9, 5, 1, "", "plot_circle"], [9, 5, 1, "", "plot_line"], [9, 5, 1, "", "plot_points"], [9, 5, 1, "", "plot_polygons"], [9, 5, 1, "", "save_plot"]], "pomdp_py.utils.templates": [[9, 1, 1, "", "DetObservationModel"], [9, 1, 1, "", "DetRewardModel"], [9, 1, 1, "", "DetTransitionModel"], [9, 1, 1, "", "SimpleAction"], [9, 1, 1, "", "SimpleObservation"], [9, 1, 1, "", "SimpleState"], [9, 1, 1, "", "TabularObservationModel"], [9, 1, 1, "", "TabularRewardModel"], [9, 1, 1, "", "TabularTransitionModel"], [9, 1, 1, "", "UniformPolicyModel"]], "pomdp_py.utils.templates.DetObservationModel": [[9, 3, 1, "", "probability"], [9, 3, 1, "", "sample"]], "pomdp_py.utils.templates.DetRewardModel": [[9, 3, 1, "", "argmax"], [9, 3, 1, "", "reward_func"], [9, 3, 1, "", "sample"]], "pomdp_py.utils.templates.DetTransitionModel": [[9, 3, 1, "", "probability"], [9, 3, 1, "", "sample"]], "pomdp_py.utils.templates.TabularObservationModel": [[9, 3, 1, "", "get_all_observations"], [9, 3, 1, "", "probability"], [9, 3, 1, "", "sample"]], "pomdp_py.utils.templates.TabularRewardModel": [[9, 3, 1, "", "sample"]], "pomdp_py.utils.templates.TabularTransitionModel": [[9, 3, 1, "", "get_all_states"], [9, 3, 1, "", "probability"], [9, 3, 1, "", "sample"]], "pomdp_py.utils.templates.UniformPolicyModel": [[9, 3, 1, "", "get_all_actions"], [9, 3, 1, "", "rollout"], [9, 3, 1, "", "sample"]], "pomdp_py.utils.test_utils": [[9, 5, 1, "", "make_tiger"], [9, 5, 1, "", "remove_files"]], "pomdp_py.utils.typ": [[9, 1, 1, "", "bcolors"], [9, 5, 1, "", "blue"], [9, 5, 1, "", "bold"], [9, 5, 1, "", "cyan"], [9, 5, 1, "", "error"], [9, 5, 1, "", "green"], [9, 5, 1, "", "info"], [9, 5, 1, "", "magenta"], [9, 5, 1, "", "note"], [9, 5, 1, "", "red"], [9, 5, 1, "", "success"], [9, 5, 1, "", "warning"], [9, 5, 1, "", "white"], [9, 5, 1, "", "yellow"]], "pomdp_py.utils.typ.bcolors": [[9, 2, 1, "", "BLUE"], [9, 2, 1, "", "BOLD"], [9, 2, 1, "", "CYAN"], [9, 2, 1, "", "ENDC"], [9, 2, 1, "", "GREEN"], [9, 2, 1, "", "MAGENTA"], [9, 2, 1, "", "RED"], [9, 2, 1, "", "WHITE"], [9, 2, 1, "", "YELLOW"], [9, 3, 1, "", "disable"], [9, 3, 1, "", "s"]], "pomdp_py.visual": [[12, 0, 0, "-", "search_tree"]], "pomdp_py.visual.search_tree": [[12, 5, 1, "", "visualize_pouct_search_tree"]]}, "objtypes": {"0": "py:module", "1": "py:class", "2": "py:attribute", "3": "py:method", "4": "py:property", "5": "py:function"}, "objnames": {"0": ["py", "module", "Python module"], "1": ["py", "class", "Python class"], "2": ["py", "attribute", "Python attribute"], "3": ["py", "method", "Python method"], "4": ["py", "property", "Python property"], "5": ["py", "function", "Python function"]}, "titleterms": {"pomdp_pi": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 18, 24, 58], "packag": [1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 12, 29, 30, 32, 34, 35, 37, 38, 39, 40, 41, 43, 44, 45, 46, 47, 49, 51, 52, 53, 54, 55, 57, 58], "algorithm": [2, 3, 4], "po_rollout": 2, "modul": [2, 3, 4, 5, 7, 8, 9, 10, 11, 12, 30, 31, 32, 33, 34, 35, 36, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58], "po_uct": 2, "pomcp": 2, "value_iter": 2, "bsp": [2, 3], "blqr": [2, 3], "visual": [2, 4, 12, 34, 45, 53], "submodul": [3, 4, 9, 12, 31, 32, 33, 34, 35, 36, 38, 39, 41, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57], "content": [3, 4, 9, 12, 18, 25, 30, 31, 32, 33, 34, 35, 38, 39, 40, 41, 47, 48, 49, 51, 52, 53, 54, 55, 57], "framework": 5, "basic": 5, "oopomdp": 5, "planner": 5, "represent": [6, 7, 8], "belief": [7, 32, 43], "histogram": [7, 8], "particl": [7, 8], "distribut": 8, "gaussian": 8, "util": [9, 10, 11, 58], "subpackag": [9, 31, 40, 48, 50, 54, 56], "color": 9, "cython_util": 9, "cpython": [9, 48, 49, 56, 57], "37m": [9, 48, 49, 56, 57], "x86_64": [9, 48, 49, 56, 57], "linux": [9, 48, 49, 56, 57], "gnu": [9, 48, 49, 56, 57], "debug": [9, 10], "treedebugg": [9, 10], "math": 9, "misc": 9, "plot": 9, "templat": 9, "test_util": 9, "typ": 9, "interfac": [11, 58], "simple_rl": [11, 58], "search_tre": 12, "build": 13, "document": [13, 24], "doc": [13, 26], "pomdp_problem": [13, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57], "note": 13, "changelog": [13, 14], "design": 15, "principl": 15, "exampl": [16, 18], "tiger": [16, 20, 56, 57], "multi": [16, 19, 42], "object": [16, 19, 42], "search": [16, 19, 42], "mo": [16, 19, 42], "prefer": 17, "base": 17, "action": [17, 33, 38, 44, 52], "prior": 17, "us": [18, 23], "extern": 18, "solver": [18, 22], "tabl": [18, 25], "convert": 18, "agent": [18, 32, 43, 51], "pomdp": [18, 19, 20, 21, 22, 25, 27], "file": 18, "solv": [18, 20], "sarsop": 18, "policygraph": 18, "alphavectorpolici": 18, "problem": [19, 42, 50], "overview": [19, 24], "implement": 19, "thi": 19, "convent": 19, "try": 19, "defin": 20, "domain": [20, 21, 33, 38, 44, 52], "model": [20, 35, 40, 41, 46, 47, 54, 55], "instanti": 20, "instanc": 20, "summari": 20, "exist": [21, 22], "case": 23, "extens": 23, "get": 24, "start": 24, "further": 24, "citat": 24, "api": 24, "refer": 24, "tool": 24, "instal": 25, "pre": 25, "py": 25, "test": [25, 31], "thing": 25, "out": 25, "docker": 25, "imag": 25, "other": 27, "librari": 27, "lasertag": 30, "light": 31, "dark": 31, "light_dark": [31, 32, 33, 34, 35], "problem_discret": 31, "observ": [33, 38, 44, 52], "state": [33, 38, 44, 52], "env": [34, 39, 45, 53], "observation_model": [35, 46, 54], "transition_model": [35, 46, 54], "load": 36, "unload": 36, "load_unload": 36, "maze": [37, 38, 39, 40, 41], "compon": [41, 47, 55], "map": 41, "task": 42, "multi_object_search": [42, 43, 44, 45, 46, 47], "example_world": [42, 50], "policy_model": [46, 54], "reward_model": [46, 54], "grid_map": [47, 55], "sensor": 47, "rocksampl": [48, 49], "rocksample_problem": [48, 49], "cython": [48, 49, 56, 57], "38": [48, 49, 56, 57], "run_rocksampl": 49, "tag": [50, 51, 52, 53, 54, 55], "constant": 50, "experi": 50, "motion_polici": 55, "tiger_problem": [56, 57], "run_tig": 57, "integr": 58, "version": 14, "1": 14, "3": 14, "07": 14, "25": 14, "2023": 14, "2": 14, "04": 14, "03": 14, "2022": 14, "11": 14, "2021": 14, "0": 14, "09": 14, "30": 14, "4": 14, "6": 14, "cancel": 14, "5": 14, "05": 14, "06": 14, "02": 14, "01": 14, "22": 14, "17": 14, "12": 14, "23": 14, "2020": 14, "pull": 14, "request": 14, "08": 14, "16": 14}, "envversion": {"sphinx.domains.c": 3, "sphinx.domains.changeset": 1, "sphinx.domains.citation": 1, "sphinx.domains.cpp": 9, "sphinx.domains.index": 1, "sphinx.domains.javascript": 3, "sphinx.domains.math": 2, "sphinx.domains.python": 4, "sphinx.domains.rst": 2, "sphinx.domains.std": 2, "sphinx.ext.intersphinx": 1, "sphinxcontrib.bibtex": 9, "sphinx.ext.viewcode": 1, "sphinx": 58}, "alltitles": {"pomdp_py": [[0, "pomdp-py"]], "pomdp_py package": [[1, "pomdp-py-package"]], "pomdp_py.algorithms.bsp.blqr module": [[3, "module-pomdp_py.algorithms.bsp.blqr"], [2, "module-pomdp_py.algorithms.bsp.blqr"]], "pomdp_py.algorithms.bsp package": [[3, "pomdp-py-algorithms-bsp-package"]], "Submodules": [[3, "submodules"], [12, "submodules"], [32, "submodules"], [33, "submodules"], [34, "submodules"], [35, "submodules"], [36, "submodules"], [38, "submodules"], [39, "submodules"], [47, "submodules"], [48, "submodules"], [50, "submodules"], [51, "submodules"], [52, "submodules"], [53, "submodules"], [54, "submodules"], [55, "submodules"], [9, "submodules"], [56, "submodules"], [4, "submodules"], [31, "submodules"], [41, "submodules"], [49, "submodules"], [57, "submodules"]], "Module contents": [[3, "module-pomdp_py.algorithms.bsp"], [12, "module-pomdp_py.visual"], [30, "module-pomdp_problems.lasertag"], [32, "module-pomdp_problems.light_dark.agent"], [33, "module-pomdp_problems.light_dark.domain"], [34, "module-pomdp_problems.light_dark.env"], [35, "module-pomdp_problems.light_dark.models"], [38, "module-pomdp_problems.maze.domain"], [39, "module-pomdp_problems.maze.env"], [40, "module-pomdp_problems.maze.models"], [47, "module-pomdp_problems.multi_object_search.models.components"], [48, "module-pomdp_problems.rocksample"], [51, "module-pomdp_problems.tag.agent"], [52, "module-pomdp_problems.tag.domain"], [53, "module-pomdp_problems.tag.env"], [54, "module-pomdp_problems.tag.models"], [55, "module-pomdp_problems.tag.models.components"], [9, "module-pomdp_py.utils"], [4, "module-contents"], [31, "module-pomdp_problems.light_dark"], [41, "module-pomdp_problems.maze.models.components"], [49, "module-pomdp_problems.rocksample.cythonize"], [57, "module-pomdp_problems.tiger.cythonize"]], "pomdp_py.framework package": [[5, "pomdp-py-framework-package"]], "pomdp_py.framework.basics module": [[5, "module-pomdp_py.framework.basics"]], "pomdp_py.framework.oopomdp module": [[5, "module-pomdp_py.framework.oopomdp"]], "pomdp_py.framework.planner module": [[5, "module-pomdp_py.framework.planner"]], "pomdp_py.representations package": [[6, "pomdp-py-representations-package"]], "pomdp_py.representations.belief package": [[7, "pomdp-py-representations-belief-package"]], "pomdp_py.representations.belief.histogram module": [[7, "module-pomdp_py.representations.belief.histogram"]], "pomdp_py.representations.belief.particles module": [[7, "module-pomdp_py.representations.belief.particles"]], "pomdp_py.representations.distribution package": [[8, "pomdp-py-representations-distribution-package"]], "pomdp_py.representations.distribution.histogram module": [[8, "module-pomdp_py.representations.distribution.histogram"]], "pomdp_py.representations.distribution.particles module": [[8, "module-pomdp_py.representations.distribution.particles"]], "pomdp_py.representations.distribution.gaussian module": [[8, "module-pomdp_py.representations.distribution.gaussian"]], "pomdp_py.utils.debugging module": [[10, "module-pomdp_py.utils.debugging"], [9, "module-pomdp_py.utils.debugging"]], "TreeDebugger": [[10, "treedebugger"], [9, "treedebugger"]], "pomdp_py.visual package": [[12, "pomdp-py-visual-package"]], "pomdp_py.visual.search_tree module": [[12, "module-pomdp_py.visual.search_tree"]], "Building Documentations": [[13, "building-documentations"]], "Building docs for pomdp_py": [[13, "building-docs-for-pomdp-py"]], "Building docs for pomdp_problems": [[13, "building-docs-for-pomdp-problems"]], "Note on Changelog": [[13, "note-on-changelog"]], "Design Principles": [[15, "design-principles"]], "Examples": [[16, "examples"]], "Tiger": [[16, "tiger"], [20, "tiger"], [56, "tiger"]], "Multi-Object Search (MOS)": [[16, "multi-object-search-mos"], [19, "multi-object-search-mos"]], "Preference-based Action Prior": [[17, "preference-based-action-prior"]], "Using External Solvers": [[18, "module-pomdp_py.utils.interfaces.solvers"]], "Table of Contents": [[18, "table-of-contents"], [25, "table-of-contents"]], "Converting a pomdp_py Agent to a POMDP File": [[18, "converting-a-pomdp-py-agent-to-a-pomdp-file"]], "Example": [[18, "example"], [18, "id2"], [18, "id4"]], "Using pomdp-solve": [[18, "using-pomdp-solve"]], "Using sarsop": [[18, "using-sarsop"]], "PolicyGraph and AlphaVectorPolicy": [[18, "policygraph-and-alphavectorpolicy"]], "Problem overview": [[19, "problem-overview"]], "Implementing this POMDP: Conventions": [[19, "implementing-this-pomdp-conventions"]], "Try it": [[19, "try-it"]], "Define the domain": [[20, "define-the-domain"]], "Define the models": [[20, "define-the-models"]], "Define the POMDP": [[20, "define-the-pomdp"]], "Instantiate the POMDP": [[20, "instantiate-the-pomdp"]], "Solve the POMDP instance": [[20, "solve-the-pomdp-instance"]], "Summary": [[20, "summary"]], "Existing POMDP Domains": [[21, "existing-pomdp-domains"]], "Existing POMDP Solvers": [[22, "existing-pomdp-solvers"]], "Use Case Extensions": [[23, "use-case-extensions"]], "docs": [[26, "docs"]], "Other POMDP Libraries": [[27, "other-pomdp-libraries"]], "pomdp_problems": [[28, "pomdp-problems"]], "pomdp_problems package": [[29, "pomdp-problems-package"]], "pomdp_problems.lasertag package": [[30, "pomdp-problems-lasertag-package"]], "pomdp_problems.light_dark.agent package": [[32, "pomdp-problems-light-dark-agent-package"]], "pomdp_problems.light_dark.agent.belief module": [[32, "module-pomdp_problems.light_dark.agent.belief"]], "pomdp_problems.light_dark.domain.action module": [[33, "module-pomdp_problems.light_dark.domain.action"]], "pomdp_problems.light_dark.domain.observation module": [[33, "module-pomdp_problems.light_dark.domain.observation"]], "pomdp_problems.light_dark.domain.state module": [[33, "module-pomdp_problems.light_dark.domain.state"]], "pomdp_problems.light_dark.env package": [[34, "pomdp-problems-light-dark-env-package"]], "pomdp_problems.light_dark.env.env module": [[34, "module-pomdp_problems.light_dark.env.env"]], "pomdp_problems.light_dark.env.visual module": [[34, "module-pomdp_problems.light_dark.env.visual"]], "pomdp_problems.light_dark.models package": [[35, "pomdp-problems-light-dark-models-package"]], "pomdp_problems.light_dark.models.observation_model module": [[35, "module-pomdp_problems.light_dark.models.observation_model"]], "pomdp_problems.light_dark.models.transition_model module": [[35, "module-pomdp_problems.light_dark.models.transition_model"]], "Load/Unload": [[36, "load-unload"]], "pomdp_problems.load_unload.load_unload module": [[36, "module-pomdp_problems.load_unload.load_unload"]], "pomdp_problems.maze package": [[37, "module-pomdp_problems.maze"]], "Maze": [[37, "maze"]], "pomdp_problems.maze.domain package": [[38, "pomdp-problems-maze-domain-package"]], "pomdp_problems.maze.domain.action module": [[38, "module-pomdp_problems.maze.domain.action"]], "pomdp_problems.maze.domain.observation module": [[38, "module-pomdp_problems.maze.domain.observation"]], "pomdp_problems.maze.domain.state module": [[38, "module-pomdp_problems.maze.domain.state"]], "pomdp_problems.maze.env package": [[39, "pomdp-problems-maze-env-package"]], "pomdp_problems.maze.env.env module": [[39, "module-pomdp_problems.maze.env.env"]], "pomdp_problems.maze.models package": [[40, "pomdp-problems-maze-models-package"]], "Subpackages": [[40, "subpackages"], [48, "subpackages"], [50, "subpackages"], [54, "subpackages"], [9, "subpackages"], [56, "subpackages"], [31, "subpackages"]], "Multi-Object Search (MOS) Task": [[42, "multi-object-search-mos-task"]], "pomdp_problems.multi_object_search.problem module": [[42, "module-pomdp_problems.multi_object_search.problem"]], "pomdp_problems.multi_object_search.example_worlds module": [[42, "module-pomdp_problems.multi_object_search.example_worlds"]], "pomdp_problems.multi_object_search.agent package": [[43, "pomdp-problems-multi-object-search-agent-package"]], "pomdp_problems.multi_object_search.agent.agent module": [[43, "module-pomdp_problems.multi_object_search.agent.agent"]], "pomdp_problems.multi_object_search.agent.belief module": [[43, "module-pomdp_problems.multi_object_search.agent.belief"]], "pomdp_problems.multi_object_search.domain package": [[44, "pomdp-problems-multi-object-search-domain-package"]], "pomdp_problems.multi_object_search.domain.action module": [[44, "module-pomdp_problems.multi_object_search.domain.action"]], "pomdp_problems.multi_object_search.domain.observation module": [[44, "module-pomdp_problems.multi_object_search.domain.observation"]], "pomdp_problems.multi_object_search.domain.state module": [[44, "module-pomdp_problems.multi_object_search.domain.state"]], "pomdp_problems.multi_object_search.env package": [[45, "pomdp-problems-multi-object-search-env-package"]], "pomdp_problems.multi_object_search.env.env module": [[45, "module-pomdp_problems.multi_object_search.env.env"]], "pomdp_problems.multi_object_search.env.visual module": [[45, "module-pomdp_problems.multi_object_search.env.visual"]], "pomdp_problems.multi_object_search.models package": [[46, "pomdp-problems-multi-object-search-models-package"]], "pomdp_problems.multi_object_search.models.observation_model module": [[46, "module-pomdp_problems.multi_object_search.models.observation_model"]], "pomdp_problems.multi_object_search.models.policy_model module": [[46, "module-pomdp_problems.multi_object_search.models.policy_model"]], "pomdp_problems.multi_object_search.models.reward_model module": [[46, "module-pomdp_problems.multi_object_search.models.reward_model"]], "pomdp_problems.multi_object_search.models.transition_model module": [[46, "module-pomdp_problems.multi_object_search.models.transition_model"]], "pomdp_problems.multi_object_search.models.components package": [[47, "pomdp-problems-multi-object-search-models-components-package"]], "pomdp_problems.multi_object_search.models.components.grid_map module": [[47, "module-pomdp_problems.multi_object_search.models.components.grid_map"]], "pomdp_problems.multi_object_search.models.components.sensor module": [[47, "module-pomdp_problems.multi_object_search.models.components.sensor"]], "RockSample": [[48, "rocksample"]], "pomdp_problems.rocksample.rocksample_problem module": [[48, "module-pomdp_problems.rocksample.rocksample_problem"], [48, "id1"]], "pomdp_problems.rocksample.cythonize.cpython-37m-x86_64-linux-gnu module": [[48, "pomdp-problems-rocksample-cythonize-cpython-37m-x86-64-linux-gnu-module"]], "pomdp_problems.rocksample.cythonize.cpython-38-x86_64-linux-gnu module": [[48, "pomdp-problems-rocksample-cythonize-cpython-38-x86-64-linux-gnu-module"]], "Tag": [[50, "tag"]], "pomdp_problems.tag.constants module": [[50, "module-pomdp_problems.tag.constants"]], "pomdp_problems.tag.example_worlds module": [[50, "module-pomdp_problems.tag.example_worlds"]], "pomdp_problems.tag.experiment module": [[50, "module-pomdp_problems.tag.experiment"]], "pomdp_problems.tag.problem module": [[50, "module-pomdp_problems.tag.problem"]], "pomdp_problems.tag.agent package": [[51, "pomdp-problems-tag-agent-package"]], "pomdp_problems.tag.agent.agent module": [[51, "module-pomdp_problems.tag.agent.agent"]], "pomdp_problems.tag.domain package": [[52, "pomdp-problems-tag-domain-package"]], "pomdp_problems.tag.domain.action module": [[52, "module-pomdp_problems.tag.domain.action"]], "pomdp_problems.tag.domain.observation module": [[52, "module-pomdp_problems.tag.domain.observation"]], "pomdp_problems.tag.domain.state module": [[52, "module-pomdp_problems.tag.domain.state"]], "pomdp_problems.tag.env package": [[53, "pomdp-problems-tag-env-package"]], "pomdp_problems.tag.env.env module": [[53, "module-pomdp_problems.tag.env.env"]], "pomdp_problems.tag.env.visual module": [[53, "module-pomdp_problems.tag.env.visual"]], "pomdp_problems.tag.models package": [[54, "pomdp-problems-tag-models-package"]], "pomdp_problems.tag.models.observation_model module": [[54, "module-pomdp_problems.tag.models.observation_model"]], "pomdp_problems.tag.models.policy_model module": [[54, "module-pomdp_problems.tag.models.policy_model"]], "pomdp_problems.tag.models.reward_model module": [[54, "module-pomdp_problems.tag.models.reward_model"]], "pomdp_problems.tag.models.transition_model module": [[54, "module-pomdp_problems.tag.models.transition_model"]], "pomdp_problems.tag.models.components package": [[55, "pomdp-problems-tag-models-components-package"]], "pomdp_problems.tag.models.components.grid_map module": [[55, "module-pomdp_problems.tag.models.components.grid_map"]], "pomdp_problems.tag.models.components.motion_policy module": [[55, "module-pomdp_problems.tag.models.components.motion_policy"]], "pomdp_py Documentation": [[24, "pomdp-py-documentation"]], "Overview": [[24, "overview"]], "Getting Started": [[24, "getting-started"]], "Further": [[24, "further"]], "Citation": [[24, "citation"]], "API References": [[24, "api-references"], [24, null]], "Tools": [[24, "tools"]], "pomdp_py.utils package": [[9, "pomdp-py-utils-package"]], "pomdp_py.utils.colors module": [[9, "module-pomdp_py.utils.colors"]], "pomdp_py.utils.cython_utils.cpython-37m-x86_64-linux-gnu module": [[9, "pomdp-py-utils-cython-utils-cpython-37m-x86-64-linux-gnu-module"]], "pomdp_py.utils.cython_utils module": [[9, "module-pomdp_py.utils.cython_utils"]], "pomdp_py.utils.math module": [[9, "module-pomdp_py.utils.math"]], "pomdp_py.utils.misc module": [[9, "module-pomdp_py.utils.misc"]], "pomdp_py.utils.plotting module": [[9, "module-pomdp_py.utils.plotting"]], "pomdp_py.utils.templates module": [[9, "module-pomdp_py.utils.templates"]], "pomdp_py.utils.test_utils module": [[9, "module-pomdp_py.utils.test_utils"]], "pomdp_py.utils.typ module": [[9, "module-pomdp_py.utils.typ"]], "pomdp_problems.tiger.cythonize.cpython-37m-x86_64-linux-gnu module": [[56, "pomdp-problems-tiger-cythonize-cpython-37m-x86-64-linux-gnu-module"]], "pomdp_problems.tiger.cythonize.cpython-38-x86_64-linux-gnu module": [[56, "pomdp-problems-tiger-cythonize-cpython-38-x86-64-linux-gnu-module"]], "pomdp_problems.tiger.tiger_problem module": [[56, "module-pomdp_problems.tiger.tiger_problem"]], "Installation": [[25, "installation"]], "Pre-installation": [[25, "pre-installation"]], "Install pomdp-py": [[25, "install-pomdp-py"]], "Test things out": [[25, "test-things-out"]], "Docker image": [[25, "docker-image"]], "pomdp_py.algorithms package": [[2, "pomdp-py-algorithms-package"]], "pomdp_py.algorithms.po_rollout module": [[2, "module-pomdp_py.algorithms.po_rollout"]], "pomdp_py.algorithms.po_uct module": [[2, "module-pomdp_py.algorithms.po_uct"]], "pomdp_py.algorithms.pomcp module": [[2, "module-pomdp_py.algorithms.pomcp"]], "pomdp_py.algorithms.value_iteration module": [[2, "module-pomdp_py.algorithms.value_iteration"]], "pomdp_py.algorithms.visual.visual module": [[2, "pomdp-py-algorithms-visual-visual-module"], [4, "pomdp-py-algorithms-visual-visual-module"]], "pomdp_py.algorithms.visual package": [[4, "pomdp-py-algorithms-visual-package"]], "pomdp_py.utils.interfaces package": [[11, "pomdp-py-utils-interfaces-package"], [58, "pomdp-py-utils-interfaces-package"]], "pomdp_py.utils.interfaces.simple_rl module": [[11, "pomdp-py-utils-interfaces-simple-rl-module"], [58, "pomdp-py-utils-interfaces-simple-rl-module"]], "Changelog": [[14, "changelog"]], "Version 1.3.3 (07/25/2023)": [[14, "version-1-3-3-07-25-2023"]], "Version 1.3.2 (04/03/2022)": [[14, "version-1-3-2-04-03-2022"]], "Version 1.3.1 (11/03/2021)": [[14, "version-1-3-1-11-03-2021"]], "Version 1.3.0.1 (09/30/2021)": [[14, "version-1-3-0-1-09-30-2021"]], "Version 1.2.4.6 (canceled)": [[14, "version-1-2-4-6-canceled"]], "Version 1.2.4.5 (07/05/2021)": [[14, "version-1-2-4-5-07-05-2021"]], "Version 1.2.4.1 (06/02/2021)": [[14, "version-1-2-4-1-06-02-2021"]], "Version 1.2.4 (06/01/2021)": [[14, "version-1-2-4-06-01-2021"]], "Version 1.2.3 (03/22/2021)": [[14, "version-1-2-3-03-22-2021"]], "Version 1.2.2.1 (01/25/2021)": [[14, "version-1-2-2-1-01-25-2021"]], "Version 1.2.2 (01/17/2021)": [[14, "version-1-2-2-01-17-2021"]], "Version 1.2.1 (12/23/2020)": [[14, "version-1-2-1-12-23-2020"]], "Pull Request #3 (08/01/2020)": [[14, "pull-request-3-08-01-2020"]], "Pull Request #1 (06/02/2020)": [[14, "pull-request-1-06-02-2020"]], "Version 1.0 - 1.2 (02/08/2020 - 02/16/2020)": [[14, "version-1-0-1-2-02-08-2020-02-16-2020"]], "Version 0.0": [[14, "version-0-0"]], "Light-Dark": [[31, "light-dark"]], "pomdp_problems.light_dark.problem_discrete module": [[31, "module-pomdp_problems.light_dark.problem_discrete"]], "pomdp_problems.light_dark.test module": [[31, "pomdp-problems-light-dark-test-module"]], "pomdp_problems.maze.models.components package": [[41, "pomdp-problems-maze-models-components-package"]], "pomdp_problems.maze.models.components.map module": [[41, "pomdp-problems-maze-models-components-map-module"]], "pomdp_problems.rocksample.cythonize package": [[49, "pomdp-problems-rocksample-cythonize-package"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.cpython-37m-x86_64-linux-gnu module": [[49, "pomdp-problems-rocksample-cythonize-rocksample-problem-cpython-37m-x86-64-linux-gnu-module"]], "pomdp_problems.rocksample.cythonize.rocksample_problem.cpython-38-x86_64-linux-gnu module": [[49, "pomdp-problems-rocksample-cythonize-rocksample-problem-cpython-38-x86-64-linux-gnu-module"]], "pomdp_problems.rocksample.cythonize.rocksample_problem module": [[49, "module-pomdp_problems.rocksample.cythonize.rocksample_problem"]], "pomdp_problems.rocksample.cythonize.run_rocksample module": [[49, "pomdp-problems-rocksample-cythonize-run-rocksample-module"]], "pomdp_problems.tiger.cythonize package": [[57, "pomdp-problems-tiger-cythonize-package"]], "pomdp_problems.tiger.cythonize.run_tiger module": [[57, "pomdp-problems-tiger-cythonize-run-tiger-module"]], "pomdp_problems.tiger.cythonize.tiger_problem.cpython-37m-x86_64-linux-gnu module": [[57, "pomdp-problems-tiger-cythonize-tiger-problem-cpython-37m-x86-64-linux-gnu-module"]], "pomdp_problems.tiger.cythonize.tiger_problem.cpython-38-x86_64-linux-gnu module": [[57, "pomdp-problems-tiger-cythonize-tiger-problem-cpython-38-x86-64-linux-gnu-module"]], "pomdp_problems.tiger.cythonize.tiger_problem module": [[57, "module-pomdp_problems.tiger.cythonize.tiger_problem"]], "Integration with simple_rl": [[58, "integration-with-simple-rl"]]}, "indexentries": {"actionprior (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.ActionPrior"]], "blqr (class in pomdp_py.algorithms.bsp.blqr)": [[2, "pomdp_py.algorithms.bsp.blqr.BLQR"]], "pomcp (class in pomdp_py.algorithms.pomcp)": [[2, "pomdp_py.algorithms.pomcp.POMCP"]], "porollout (class in pomdp_py.algorithms.po_rollout)": [[2, "pomdp_py.algorithms.po_rollout.PORollout"]], "pouct (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.POUCT"]], "qnode (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.QNode"]], "randomrollout (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.RandomRollout"]], "rolloutpolicy (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.RolloutPolicy"]], "rootvnode (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.RootVNode"]], "rootvnodeparticles (class in pomdp_py.algorithms.pomcp)": [[2, "pomdp_py.algorithms.pomcp.RootVNodeParticles"]], "treenode (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.TreeNode"]], "vnode (class in pomdp_py.algorithms.po_uct)": [[2, "pomdp_py.algorithms.po_uct.VNode"]], "vnodeparticles (class in pomdp_py.algorithms.pomcp)": [[2, "pomdp_py.algorithms.pomcp.VNodeParticles"]], "valueiteration (class in pomdp_py.algorithms.value_iteration)": [[2, "pomdp_py.algorithms.value_iteration.ValueIteration"]], "argmax() (pomdp_py.algorithms.po_uct.vnode method)": [[2, "pomdp_py.algorithms.po_uct.VNode.argmax"]], "belief (pomdp_py.algorithms.pomcp.rootvnodeparticles attribute)": [[2, "pomdp_py.algorithms.pomcp.RootVNodeParticles.belief"]], "belief (pomdp_py.algorithms.pomcp.vnodeparticles attribute)": [[2, "pomdp_py.algorithms.pomcp.VNodeParticles.belief"]], "children (pomdp_py.algorithms.po_uct.treenode attribute)": [[2, "pomdp_py.algorithms.po_uct.TreeNode.children"]], "clear_agent() (pomdp_py.algorithms.po_rollout.porollout method)": [[2, "pomdp_py.algorithms.po_rollout.PORollout.clear_agent"]], "clear_agent() (pomdp_py.algorithms.po_uct.pouct method)": [[2, "pomdp_py.algorithms.po_uct.POUCT.clear_agent"]], "create_plan() (pomdp_py.algorithms.bsp.blqr.blqr method)": [[2, "pomdp_py.algorithms.bsp.blqr.BLQR.create_plan"]], "ekf_update_mlo() (pomdp_py.algorithms.bsp.blqr.blqr method)": [[2, "pomdp_py.algorithms.bsp.blqr.BLQR.ekf_update_mlo"]], "from_vnode() (pomdp_py.algorithms.po_uct.rootvnode class method)": [[2, "pomdp_py.algorithms.po_uct.RootVNode.from_vnode"]], "from_vnode() (pomdp_py.algorithms.pomcp.rootvnodeparticles class method)": [[2, "pomdp_py.algorithms.pomcp.RootVNodeParticles.from_vnode"]], "get_preferred_actions() (pomdp_py.algorithms.po_uct.actionprior method)": [[2, "pomdp_py.algorithms.po_uct.ActionPrior.get_preferred_actions"]], "history (pomdp_py.algorithms.po_uct.rootvnode attribute)": [[2, "pomdp_py.algorithms.po_uct.RootVNode.history"]], "integrate_belief_segment() (pomdp_py.algorithms.bsp.blqr.blqr method)": [[2, "pomdp_py.algorithms.bsp.blqr.BLQR.integrate_belief_segment"]], "interpret_sqp_plan() (pomdp_py.algorithms.bsp.blqr.blqr method)": [[2, "pomdp_py.algorithms.bsp.blqr.BLQR.interpret_sqp_plan"]], "last_best_reward (pomdp_py.algorithms.po_rollout.porollout attribute)": [[2, "pomdp_py.algorithms.po_rollout.PORollout.last_best_reward"]], "last_num_sims (pomdp_py.algorithms.po_uct.pouct attribute)": [[2, "pomdp_py.algorithms.po_uct.POUCT.last_num_sims"]], "last_planning_time (pomdp_py.algorithms.po_uct.pouct attribute)": [[2, "pomdp_py.algorithms.po_uct.POUCT.last_planning_time"]], "module": [[2, "module-pomdp_py.algorithms.bsp.blqr"], [2, "module-pomdp_py.algorithms.po_rollout"], [2, "module-pomdp_py.algorithms.po_uct"], [2, "module-pomdp_py.algorithms.pomcp"], [2, "module-pomdp_py.algorithms.value_iteration"], [9, "module-pomdp_py.utils"], [9, "module-pomdp_py.utils.colors"], [9, "module-pomdp_py.utils.cython_utils"], [9, "module-pomdp_py.utils.debugging"], [9, "module-pomdp_py.utils.math"], [9, "module-pomdp_py.utils.misc"], [9, "module-pomdp_py.utils.plotting"], [9, "module-pomdp_py.utils.templates"], [9, "module-pomdp_py.utils.test_utils"], [9, "module-pomdp_py.utils.typ"], [31, "module-pomdp_problems.light_dark"], [31, "module-pomdp_problems.light_dark.problem_discrete"], [40, "module-pomdp_problems.maze.models"], [41, "module-pomdp_problems.maze.models.components"], [48, "module-0"], [48, "module-pomdp_problems.rocksample"], [48, "module-pomdp_problems.rocksample.rocksample_problem"], [49, "module-pomdp_problems.rocksample.cythonize"], [49, "module-pomdp_problems.rocksample.cythonize.rocksample_problem"], [56, "module-pomdp_problems.tiger.tiger_problem"], [57, "module-pomdp_problems.tiger.cythonize"], [57, "module-pomdp_problems.tiger.cythonize.tiger_problem"]], "num_visits (pomdp_py.algorithms.po_uct.treenode attribute)": [[2, "pomdp_py.algorithms.po_uct.TreeNode.num_visits"]], "plan() (pomdp_py.algorithms.po_rollout.porollout method)": [[2, "pomdp_py.algorithms.po_rollout.PORollout.plan"]], "plan() (pomdp_py.algorithms.po_uct.pouct method)": [[2, "pomdp_py.algorithms.po_uct.POUCT.plan"]], "plan() (pomdp_py.algorithms.pomcp.pomcp method)": [[2, "pomdp_py.algorithms.pomcp.POMCP.plan"]], "plan() (pomdp_py.algorithms.value_iteration.valueiteration method)": [[2, "pomdp_py.algorithms.value_iteration.ValueIteration.plan"]], "pomdp_py.algorithms.bsp.blqr": [[2, "module-pomdp_py.algorithms.bsp.blqr"]], "pomdp_py.algorithms.po_rollout": [[2, "module-pomdp_py.algorithms.po_rollout"]], "pomdp_py.algorithms.po_uct": [[2, "module-pomdp_py.algorithms.po_uct"]], "pomdp_py.algorithms.pomcp": [[2, "module-pomdp_py.algorithms.pomcp"]], "pomdp_py.algorithms.value_iteration": [[2, "module-pomdp_py.algorithms.value_iteration"]], "print_children_value() (pomdp_py.algorithms.po_uct.vnode method)": [[2, "pomdp_py.algorithms.po_uct.VNode.print_children_value"]], "rollout() (pomdp_py.algorithms.po_uct.randomrollout method)": [[2, "pomdp_py.algorithms.po_uct.RandomRollout.rollout"]], "rollout() (pomdp_py.algorithms.po_uct.rolloutpolicy method)": [[2, "pomdp_py.algorithms.po_uct.RolloutPolicy.rollout"]], "segmented_cost_function() (pomdp_py.algorithms.bsp.blqr.blqr method)": [[2, "pomdp_py.algorithms.bsp.blqr.BLQR.segmented_cost_function"]], "set_rollout_policy() (pomdp_py.algorithms.po_rollout.porollout method)": [[2, "pomdp_py.algorithms.po_rollout.PORollout.set_rollout_policy"]], "set_rollout_policy() (pomdp_py.algorithms.po_uct.pouct method)": [[2, "pomdp_py.algorithms.po_uct.POUCT.set_rollout_policy"]], "update() (pomdp_py.algorithms.po_rollout.porollout method)": [[2, "pomdp_py.algorithms.po_rollout.PORollout.update"]], "update() (pomdp_py.algorithms.po_uct.pouct method)": [[2, "pomdp_py.algorithms.po_uct.POUCT.update"]], "update() (pomdp_py.algorithms.pomcp.pomcp method)": [[2, "pomdp_py.algorithms.pomcp.POMCP.update"]], "update_agent_belief (pomdp_py.algorithms.po_rollout.porollout attribute)": [[2, "pomdp_py.algorithms.po_rollout.PORollout.update_agent_belief"]], "update_agent_belief (pomdp_py.algorithms.pomcp.pomcp attribute)": [[2, "pomdp_py.algorithms.pomcp.POMCP.update_agent_belief"]], "updates_agent_belief (pomdp_py.algorithms.po_uct.pouct attribute)": [[2, "pomdp_py.algorithms.po_uct.POUCT.updates_agent_belief"]], "value (pomdp_py.algorithms.po_uct.treenode attribute)": [[2, "pomdp_py.algorithms.po_uct.TreeNode.value"]], "value (pomdp_py.algorithms.po_uct.vnode attribute)": [[2, "pomdp_py.algorithms.po_uct.VNode.value"]], "blue (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.BLUE"]], "bold (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.BOLD"]], "cyan (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.CYAN"]], "detobservationmodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.DetObservationModel"]], "detrewardmodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.DetRewardModel"]], "dettransitionmodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.DetTransitionModel"]], "endc (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.ENDC"]], "green (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.GREEN"]], "magenta (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.MAGENTA"]], "red (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.RED"]], "r_between() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.R_between"]], "r_x() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.R_x"]], "r_y() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.R_y"]], "r_z() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.R_z"]], "subscript (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.SUBSCRIPT"]], "simpleaction (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.SimpleAction"]], "simpleobservation (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.SimpleObservation"]], "simplestate (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.SimpleState"]], "t() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.T"]], "tabularobservationmodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.TabularObservationModel"]], "tabularrewardmodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.TabularRewardModel"]], "tabulartransitionmodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.TabularTransitionModel"]], "treedebugger (class in pomdp_py.utils.debugging)": [[9, "pomdp_py.utils.debugging.TreeDebugger"]], "uniformpolicymodel (class in pomdp_py.utils.templates)": [[9, "pomdp_py.utils.templates.UniformPolicyModel"]], "white (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.WHITE"]], "yellow (pomdp_py.utils.typ.bcolors attribute)": [[9, "pomdp_py.utils.typ.bcolors.YELLOW"]], "approx_equal() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.approx_equal"]], "argmax() (pomdp_py.utils.templates.detrewardmodel method)": [[9, "pomdp_py.utils.templates.DetRewardModel.argmax"]], "b (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.b"]], "back() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.back"]], "bcolors (class in pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.bcolors"]], "bestseq (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.bestseq"]], "bestseqd() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.bestseqd"]], "blue() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.blue"]], "bold() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.bold"]], "bottomleft (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.bottomleft"]], "bottomright (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.bottomright"]], "bottomt (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.bottomt"]], "c (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.c"]], "clear (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.clear"]], "cyan() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.cyan"]], "d (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.d"]], "depth (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.depth"]], "det_dict_hash() (in module pomdp_py.utils.cython_utils)": [[9, "pomdp_py.utils.cython_utils.det_dict_hash"]], "disable() (pomdp_py.utils.typ.bcolors static method)": [[9, "pomdp_py.utils.typ.bcolors.disable"]], "down (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.down"]], "error() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.error"]], "euclidean_dist() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.euclidean_dist"]], "get_all_actions() (pomdp_py.utils.templates.uniformpolicymodel method)": [[9, "pomdp_py.utils.templates.UniformPolicyModel.get_all_actions"]], "get_all_observations() (pomdp_py.utils.templates.tabularobservationmodel method)": [[9, "pomdp_py.utils.templates.TabularObservationModel.get_all_observations"]], "get_all_states() (pomdp_py.utils.templates.tabulartransitionmodel method)": [[9, "pomdp_py.utils.templates.TabularTransitionModel.get_all_states"]], "green() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.green"]], "hex_to_rgb() (in module pomdp_py.utils.colors)": [[9, "pomdp_py.utils.colors.hex_to_rgb"]], "hline (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.hline"]], "info() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.info"]], "interpret_color() (in module pomdp_py.utils.debugging)": [[9, "pomdp_py.utils.debugging.interpret_color"]], "intersect (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.intersect"]], "inverse_color_hex() (in module pomdp_py.utils.colors)": [[9, "pomdp_py.utils.colors.inverse_color_hex"]], "inverse_color_rgb() (in module pomdp_py.utils.colors)": [[9, "pomdp_py.utils.colors.inverse_color_rgb"]], "json_safe() (in module pomdp_py.utils.misc)": [[9, "pomdp_py.utils.misc.json_safe"]], "l() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.l"]], "layer() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.layer"]], "leaf (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.leaf"]], "left (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.left"]], "leftt (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.leftt"]], "lighter() (in module pomdp_py.utils.colors)": [[9, "pomdp_py.utils.colors.lighter"]], "longbottomleft (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.longbottomleft"]], "longbottomright (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.longbottomright"]], "longleft (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.longleft"]], "longright (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.longright"]], "longtopleft (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.longtopleft"]], "longtopright (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.longtopright"]], "magenta() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.magenta"]], "make_tiger() (in module pomdp_py.utils.test_utils)": [[9, "pomdp_py.utils.test_utils.make_tiger"]], "mark() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.mark"]], "mark_path() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.mark_path"]], "mark_sequence() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.mark_sequence"]], "markp() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.markp"]], "mbp (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.mbp"]], "nl (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.nl"]], "nn (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.nn"]], "note() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.note"]], "nq (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.nq"]], "num_layers (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.num_layers"]], "num_nodes() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.num_nodes"]], "nv (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.nv"]], "p() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.p"]], "path() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.path"]], "path_to() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.path_to"]], "plot_circle() (in module pomdp_py.utils.plotting)": [[9, "pomdp_py.utils.plotting.plot_circle"]], "plot_line() (in module pomdp_py.utils.plotting)": [[9, "pomdp_py.utils.plotting.plot_line"]], "plot_points() (in module pomdp_py.utils.plotting)": [[9, "pomdp_py.utils.plotting.plot_points"]], "plot_polygons() (in module pomdp_py.utils.plotting)": [[9, "pomdp_py.utils.plotting.plot_polygons"]], "pm (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.pm"]], "pomdp_py.utils": [[9, "module-pomdp_py.utils"]], "pomdp_py.utils.colors": [[9, "module-pomdp_py.utils.colors"]], "pomdp_py.utils.cython_utils": [[9, "module-pomdp_py.utils.cython_utils"]], "pomdp_py.utils.debugging": [[9, "module-pomdp_py.utils.debugging"]], "pomdp_py.utils.math": [[9, "module-pomdp_py.utils.math"]], "pomdp_py.utils.misc": [[9, "module-pomdp_py.utils.misc"]], "pomdp_py.utils.plotting": [[9, "module-pomdp_py.utils.plotting"]], "pomdp_py.utils.templates": [[9, "module-pomdp_py.utils.templates"]], "pomdp_py.utils.test_utils": [[9, "module-pomdp_py.utils.test_utils"]], "pomdp_py.utils.typ": [[9, "module-pomdp_py.utils.typ"]], "pp (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.pp"]], "preferred_actions() (pomdp_py.utils.debugging.treedebugger static method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.preferred_actions"]], "probability() (pomdp_py.utils.templates.detobservationmodel method)": [[9, "pomdp_py.utils.templates.DetObservationModel.probability"]], "probability() (pomdp_py.utils.templates.dettransitionmodel method)": [[9, "pomdp_py.utils.templates.DetTransitionModel.probability"]], "probability() (pomdp_py.utils.templates.tabularobservationmodel method)": [[9, "pomdp_py.utils.templates.TabularObservationModel.probability"]], "probability() (pomdp_py.utils.templates.tabulartransitionmodel method)": [[9, "pomdp_py.utils.templates.TabularTransitionModel.probability"]], "proj() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.proj"]], "r (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.r"]], "random_unique_color() (in module pomdp_py.utils.colors)": [[9, "pomdp_py.utils.colors.random_unique_color"]], "red() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.red"]], "remap() (in module pomdp_py.utils.misc)": [[9, "pomdp_py.utils.misc.remap"]], "remove_files() (in module pomdp_py.utils.test_utils)": [[9, "pomdp_py.utils.test_utils.remove_files"]], "reward_func() (pomdp_py.utils.templates.detrewardmodel method)": [[9, "pomdp_py.utils.templates.DetRewardModel.reward_func"]], "rgb_to_hex() (in module pomdp_py.utils.colors)": [[9, "pomdp_py.utils.colors.rgb_to_hex"]], "right (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.right"]], "rightt (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.rightt"]], "rollout() (pomdp_py.utils.templates.uniformpolicymodel method)": [[9, "pomdp_py.utils.templates.UniformPolicyModel.rollout"]], "root (pomdp_py.utils.debugging.treedebugger property)": [[9, "pomdp_py.utils.debugging.TreeDebugger.root"]], "s() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.s"]], "s() (pomdp_py.utils.typ.bcolors static method)": [[9, "pomdp_py.utils.typ.bcolors.s"]], "safe_slice() (in module pomdp_py.utils.misc)": [[9, "pomdp_py.utils.misc.safe_slice"]], "sample() (pomdp_py.utils.templates.detobservationmodel method)": [[9, "pomdp_py.utils.templates.DetObservationModel.sample"]], "sample() (pomdp_py.utils.templates.detrewardmodel method)": [[9, "pomdp_py.utils.templates.DetRewardModel.sample"]], "sample() (pomdp_py.utils.templates.dettransitionmodel method)": [[9, "pomdp_py.utils.templates.DetTransitionModel.sample"]], "sample() (pomdp_py.utils.templates.tabularobservationmodel method)": [[9, "pomdp_py.utils.templates.TabularObservationModel.sample"]], "sample() (pomdp_py.utils.templates.tabularrewardmodel method)": [[9, "pomdp_py.utils.templates.TabularRewardModel.sample"]], "sample() (pomdp_py.utils.templates.tabulartransitionmodel method)": [[9, "pomdp_py.utils.templates.TabularTransitionModel.sample"]], "sample() (pomdp_py.utils.templates.uniformpolicymodel method)": [[9, "pomdp_py.utils.templates.UniformPolicyModel.sample"]], "save_plot() (in module pomdp_py.utils.plotting)": [[9, "pomdp_py.utils.plotting.save_plot"]], "shadebar (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.shadebar"]], "similar() (in module pomdp_py.utils.misc)": [[9, "pomdp_py.utils.misc.similar"]], "single_node_str() (pomdp_py.utils.debugging.treedebugger static method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.single_node_str"]], "sorted_by_str() (in module pomdp_py.utils.debugging)": [[9, "pomdp_py.utils.debugging.sorted_by_str"]], "special_char (class in pomdp_py.utils.misc)": [[9, "pomdp_py.utils.misc.special_char"]], "step() (pomdp_py.utils.debugging.treedebugger method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.step"]], "success() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.success"]], "to_radians() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.to_radians"]], "topleft (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.topleft"]], "topright (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.topright"]], "topt (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.topt"]], "tree_stats() (pomdp_py.utils.debugging.treedebugger static method)": [[9, "pomdp_py.utils.debugging.TreeDebugger.tree_stats"]], "up (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.up"]], "vec() (in module pomdp_py.utils.math)": [[9, "pomdp_py.utils.math.vec"]], "vline (pomdp_py.utils.misc.special_char attribute)": [[9, "pomdp_py.utils.misc.special_char.vline"]], "warning() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.warning"]], "white() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.white"]], "yellow() (in module pomdp_py.utils.typ)": [[9, "pomdp_py.utils.typ.yellow"]], "discretelightdark (class in pomdp_problems.light_dark.problem_discrete)": [[31, "pomdp_problems.light_dark.problem_discrete.DiscreteLightDark"]], "pomdp_problems.light_dark": [[31, "module-pomdp_problems.light_dark"]], "pomdp_problems.light_dark.problem_discrete": [[31, "module-pomdp_problems.light_dark.problem_discrete"]], "pomdp_problems.maze.models": [[40, "module-pomdp_problems.maze.models"]], "pomdp_problems.maze.models.components": [[41, "module-pomdp_problems.maze.models.components"]], "action (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id8"], [48, "pomdp_problems.rocksample.rocksample_problem.Action"]], "bad (pomdp_problems.rocksample.rocksample_problem.rocktype attribute)": [[48, "id4"], [48, "pomdp_problems.rocksample.rocksample_problem.RockType.BAD"]], "checkaction (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id15"], [48, "pomdp_problems.rocksample.rocksample_problem.CheckAction"]], "east (pomdp_problems.rocksample.rocksample_problem.moveaction attribute)": [[48, "id10"], [48, "pomdp_problems.rocksample.rocksample_problem.MoveAction.EAST"]], "good (pomdp_problems.rocksample.rocksample_problem.rocktype attribute)": [[48, "id3"], [48, "pomdp_problems.rocksample.rocksample_problem.RockType.GOOD"]], "moveaction (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id9"], [48, "pomdp_problems.rocksample.rocksample_problem.MoveAction"]], "north (pomdp_problems.rocksample.rocksample_problem.moveaction attribute)": [[48, "id12"], [48, "pomdp_problems.rocksample.rocksample_problem.MoveAction.NORTH"]], "observation (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id16"], [48, "pomdp_problems.rocksample.rocksample_problem.Observation"]], "rsobservationmodel (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id21"], [48, "pomdp_problems.rocksample.rocksample_problem.RSObservationModel"]], "rspolicymodel (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id29"], [48, "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel"]], "rsrewardmodel (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id25"], [48, "pomdp_problems.rocksample.rocksample_problem.RSRewardModel"]], "rstransitionmodel (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id17"], [48, "pomdp_problems.rocksample.rocksample_problem.RSTransitionModel"]], "rocksampleproblem (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id35"], [48, "pomdp_problems.rocksample.rocksample_problem.RockSampleProblem"]], "rocktype (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id2"], [48, "pomdp_problems.rocksample.rocksample_problem.RockType"]], "south (pomdp_problems.rocksample.rocksample_problem.moveaction attribute)": [[48, "id13"], [48, "pomdp_problems.rocksample.rocksample_problem.MoveAction.SOUTH"]], "sampleaction (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id14"], [48, "pomdp_problems.rocksample.rocksample_problem.SampleAction"]], "state (class in pomdp_problems.rocksample.rocksample_problem)": [[48, "id7"], [48, "pomdp_problems.rocksample.rocksample_problem.State"]], "west (pomdp_problems.rocksample.rocksample_problem.moveaction attribute)": [[48, "id11"], [48, "pomdp_problems.rocksample.rocksample_problem.MoveAction.WEST"]], "argmax() (pomdp_problems.rocksample.rocksample_problem.rsobservationmodel method)": [[48, "id24"], [48, "pomdp_problems.rocksample.rocksample_problem.RSObservationModel.argmax"]], "argmax() (pomdp_problems.rocksample.rocksample_problem.rspolicymodel method)": [[48, "id32"], [48, "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel.argmax"]], "argmax() (pomdp_problems.rocksample.rocksample_problem.rsrewardmodel method)": [[48, "id27"], [48, "pomdp_problems.rocksample.rocksample_problem.RSRewardModel.argmax"]], "argmax() (pomdp_problems.rocksample.rocksample_problem.rstransitionmodel method)": [[48, "id20"], [48, "pomdp_problems.rocksample.rocksample_problem.RSTransitionModel.argmax"]], "euclidean_dist() (in module pomdp_problems.rocksample.rocksample_problem)": [[48, "id0"], [48, "pomdp_problems.rocksample.rocksample_problem.euclidean_dist"]], "generate_instance() (pomdp_problems.rocksample.rocksample_problem.rocksampleproblem static method)": [[48, "id38"], [48, "pomdp_problems.rocksample.rocksample_problem.RockSampleProblem.generate_instance"]], "get_all_actions() (pomdp_problems.rocksample.rocksample_problem.rspolicymodel method)": [[48, "id33"], [48, "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel.get_all_actions"]], "in_exit_area() (pomdp_problems.rocksample.rocksample_problem.rocksampleproblem method)": [[48, "id37"], [48, "pomdp_problems.rocksample.rocksample_problem.RockSampleProblem.in_exit_area"]], "init_particles_belief() (in module pomdp_problems.rocksample.rocksample_problem)": [[48, "id41"], [48, "pomdp_problems.rocksample.rocksample_problem.init_particles_belief"]], "invert() (pomdp_problems.rocksample.rocksample_problem.rocktype static method)": [[48, "id5"], [48, "pomdp_problems.rocksample.rocksample_problem.RockType.invert"]], "main() (in module pomdp_problems.rocksample.rocksample_problem)": [[48, "id42"], [48, "pomdp_problems.rocksample.rocksample_problem.main"]], "pomdp_problems.rocksample": [[48, "module-pomdp_problems.rocksample"]], "pomdp_problems.rocksample.rocksample_problem": [[48, "module-0"], [48, "module-pomdp_problems.rocksample.rocksample_problem"]], "print_state() (pomdp_problems.rocksample.rocksample_problem.rocksampleproblem method)": [[48, "id39"], [48, "pomdp_problems.rocksample.rocksample_problem.RockSampleProblem.print_state"]], "probability() (pomdp_problems.rocksample.rocksample_problem.rsobservationmodel method)": [[48, "id22"], [48, "pomdp_problems.rocksample.rocksample_problem.RSObservationModel.probability"]], "probability() (pomdp_problems.rocksample.rocksample_problem.rspolicymodel method)": [[48, "id31"], [48, "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel.probability"]], "probability() (pomdp_problems.rocksample.rocksample_problem.rsrewardmodel method)": [[48, "id28"], [48, "pomdp_problems.rocksample.rocksample_problem.RSRewardModel.probability"]], "probability() (pomdp_problems.rocksample.rocksample_problem.rstransitionmodel method)": [[48, "id18"], [48, "pomdp_problems.rocksample.rocksample_problem.RSTransitionModel.probability"]], "random() (pomdp_problems.rocksample.rocksample_problem.rocktype static method)": [[48, "id6"], [48, "pomdp_problems.rocksample.rocksample_problem.RockType.random"]], "random_free_location() (pomdp_problems.rocksample.rocksample_problem.rocksampleproblem static method)": [[48, "id36"], [48, "pomdp_problems.rocksample.rocksample_problem.RockSampleProblem.random_free_location"]], "rollout() (pomdp_problems.rocksample.rocksample_problem.rspolicymodel method)": [[48, "id34"], [48, "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel.rollout"]], "sample() (pomdp_problems.rocksample.rocksample_problem.rsobservationmodel method)": [[48, "id23"], [48, "pomdp_problems.rocksample.rocksample_problem.RSObservationModel.sample"]], "sample() (pomdp_problems.rocksample.rocksample_problem.rspolicymodel method)": [[48, "id30"], [48, "pomdp_problems.rocksample.rocksample_problem.RSPolicyModel.sample"]], "sample() (pomdp_problems.rocksample.rocksample_problem.rsrewardmodel method)": [[48, "id26"], [48, "pomdp_problems.rocksample.rocksample_problem.RSRewardModel.sample"]], "sample() (pomdp_problems.rocksample.rocksample_problem.rstransitionmodel method)": [[48, "id19"], [48, "pomdp_problems.rocksample.rocksample_problem.RSTransitionModel.sample"]], "test_planner() (in module pomdp_problems.rocksample.rocksample_problem)": [[48, "id40"], [48, "pomdp_problems.rocksample.rocksample_problem.test_planner"]], "bad (pomdp_problems.rocksample.cythonize.rocksample_problem.rocktype attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockType.BAD"]], "checkaction (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.CheckAction"]], "east (pomdp_problems.rocksample.cythonize.rocksample_problem.moveaction attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction.EAST"]], "good (pomdp_problems.rocksample.cythonize.rocksample_problem.rocktype attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockType.GOOD"]], "moveaction (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction"]], "north (pomdp_problems.rocksample.cythonize.rocksample_problem.moveaction attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction.NORTH"]], "rsaction (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSAction"]], "rsobservation (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservation"]], "rsobservationmodel (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservationModel"]], "rspolicymodel (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel"]], "rsrewardmodel (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSRewardModel"]], "rsstate (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSState"]], "rstransitionmodel (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSTransitionModel"]], "rocksampleproblem (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockSampleProblem"]], "rocktype (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockType"]], "south (pomdp_problems.rocksample.cythonize.rocksample_problem.moveaction attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction.SOUTH"]], "sampleaction (class in pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.SampleAction"]], "west (pomdp_problems.rocksample.cythonize.rocksample_problem.moveaction attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction.WEST"]], "argmax() (pomdp_problems.rocksample.cythonize.rocksample_problem.rsobservationmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservationModel.argmax"]], "argmax() (pomdp_problems.rocksample.cythonize.rocksample_problem.rspolicymodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel.argmax"]], "argmax() (pomdp_problems.rocksample.cythonize.rocksample_problem.rsrewardmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSRewardModel.argmax"]], "argmax() (pomdp_problems.rocksample.cythonize.rocksample_problem.rstransitionmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSTransitionModel.argmax"]], "euclidean_dist() (in module pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.euclidean_dist"]], "generate_instance() (pomdp_problems.rocksample.cythonize.rocksample_problem.rocksampleproblem static method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockSampleProblem.generate_instance"]], "get_all_actions() (pomdp_problems.rocksample.cythonize.rocksample_problem.rspolicymodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel.get_all_actions"]], "in_exit_area() (pomdp_problems.rocksample.cythonize.rocksample_problem.rocksampleproblem method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockSampleProblem.in_exit_area"]], "init_particles_belief() (in module pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.init_particles_belief"]], "invert() (pomdp_problems.rocksample.cythonize.rocksample_problem.rocktype static method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockType.invert"]], "main() (in module pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.main"]], "motion (pomdp_problems.rocksample.cythonize.rocksample_problem.moveaction attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.MoveAction.motion"]], "pomdp_problems.rocksample.cythonize": [[49, "module-pomdp_problems.rocksample.cythonize"]], "pomdp_problems.rocksample.cythonize.rocksample_problem": [[49, "module-pomdp_problems.rocksample.cythonize.rocksample_problem"]], "position (pomdp_problems.rocksample.cythonize.rocksample_problem.rsstate attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSState.position"]], "print_state() (pomdp_problems.rocksample.cythonize.rocksample_problem.rocksampleproblem method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockSampleProblem.print_state"]], "probability() (pomdp_problems.rocksample.cythonize.rocksample_problem.rsobservationmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservationModel.probability"]], "probability() (pomdp_problems.rocksample.cythonize.rocksample_problem.rspolicymodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel.probability"]], "probability() (pomdp_problems.rocksample.cythonize.rocksample_problem.rsrewardmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSRewardModel.probability"]], "probability() (pomdp_problems.rocksample.cythonize.rocksample_problem.rstransitionmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSTransitionModel.probability"]], "quality (pomdp_problems.rocksample.cythonize.rocksample_problem.rsobservation attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservation.quality"]], "random() (pomdp_problems.rocksample.cythonize.rocksample_problem.rocktype static method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockType.random"]], "random_free_location() (pomdp_problems.rocksample.cythonize.rocksample_problem.rocksampleproblem static method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RockSampleProblem.random_free_location"]], "rock_id (pomdp_problems.rocksample.cythonize.rocksample_problem.checkaction attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.CheckAction.rock_id"]], "rocktypes (pomdp_problems.rocksample.cythonize.rocksample_problem.rsstate attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSState.rocktypes"]], "rollout() (pomdp_problems.rocksample.cythonize.rocksample_problem.rspolicymodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel.rollout"]], "sample() (pomdp_problems.rocksample.cythonize.rocksample_problem.rsobservationmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSObservationModel.sample"]], "sample() (pomdp_problems.rocksample.cythonize.rocksample_problem.rspolicymodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSPolicyModel.sample"]], "sample() (pomdp_problems.rocksample.cythonize.rocksample_problem.rsrewardmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSRewardModel.sample"]], "sample() (pomdp_problems.rocksample.cythonize.rocksample_problem.rstransitionmodel method)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSTransitionModel.sample"]], "terminal (pomdp_problems.rocksample.cythonize.rocksample_problem.rsstate attribute)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.RSState.terminal"]], "test_planner() (in module pomdp_problems.rocksample.cythonize.rocksample_problem)": [[49, "pomdp_problems.rocksample.cythonize.rocksample_problem.test_planner"]], "actions (pomdp_problems.tiger.tiger_problem.policymodel attribute)": [[56, "pomdp_problems.tiger.tiger_problem.PolicyModel.ACTIONS"]], "observationmodel (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.ObservationModel"]], "policymodel (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.PolicyModel"]], "rewardmodel (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.RewardModel"]], "tigeraction (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.TigerAction"]], "tigerobservation (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.TigerObservation"]], "tigerproblem (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.TigerProblem"]], "tigerstate (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.TigerState"]], "transitionmodel (class in pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.TransitionModel"]], "create() (pomdp_problems.tiger.tiger_problem.tigerproblem static method)": [[56, "pomdp_problems.tiger.tiger_problem.TigerProblem.create"]], "get_all_actions() (pomdp_problems.tiger.tiger_problem.policymodel method)": [[56, "pomdp_problems.tiger.tiger_problem.PolicyModel.get_all_actions"]], "get_all_observations() (pomdp_problems.tiger.tiger_problem.observationmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.ObservationModel.get_all_observations"]], "get_all_states() (pomdp_problems.tiger.tiger_problem.transitionmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.TransitionModel.get_all_states"]], "main() (in module pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.main"]], "other() (pomdp_problems.tiger.tiger_problem.tigerstate method)": [[56, "pomdp_problems.tiger.tiger_problem.TigerState.other"]], "pomdp_problems.tiger.tiger_problem": [[56, "module-pomdp_problems.tiger.tiger_problem"]], "probability() (pomdp_problems.tiger.tiger_problem.observationmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.ObservationModel.probability"]], "probability() (pomdp_problems.tiger.tiger_problem.transitionmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.TransitionModel.probability"]], "rollout() (pomdp_problems.tiger.tiger_problem.policymodel method)": [[56, "pomdp_problems.tiger.tiger_problem.PolicyModel.rollout"]], "sample() (pomdp_problems.tiger.tiger_problem.observationmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.ObservationModel.sample"]], "sample() (pomdp_problems.tiger.tiger_problem.policymodel method)": [[56, "pomdp_problems.tiger.tiger_problem.PolicyModel.sample"]], "sample() (pomdp_problems.tiger.tiger_problem.rewardmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.RewardModel.sample"]], "sample() (pomdp_problems.tiger.tiger_problem.transitionmodel method)": [[56, "pomdp_problems.tiger.tiger_problem.TransitionModel.sample"]], "test_planner() (in module pomdp_problems.tiger.tiger_problem)": [[56, "pomdp_problems.tiger.tiger_problem.test_planner"]], "actions (pomdp_problems.tiger.cythonize.tiger_problem.tigerproblem attribute)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerProblem.ACTIONS"]], "observations (pomdp_problems.tiger.cythonize.tiger_problem.tigerproblem attribute)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerProblem.OBSERVATIONS"]], "states (pomdp_problems.tiger.cythonize.tiger_problem.tigerproblem attribute)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerProblem.STATES"]], "tigeraction (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerAction"]], "tigerobservation (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservation"]], "tigerobservationmodel (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel"]], "tigerpolicymodel (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerPolicyModel"]], "tigerproblem (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerProblem"]], "tigerrewardmodel (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerRewardModel"]], "tigerstate (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerState"]], "tigertransitionmodel (class in pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel"]], "argmax() (pomdp_problems.tiger.cythonize.tiger_problem.tigerobservationmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel.argmax"]], "argmax() (pomdp_problems.tiger.cythonize.tiger_problem.tigerpolicymodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerPolicyModel.argmax"]], "argmax() (pomdp_problems.tiger.cythonize.tiger_problem.tigerrewardmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerRewardModel.argmax"]], "argmax() (pomdp_problems.tiger.cythonize.tiger_problem.tigertransitionmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel.argmax"]], "build_actions() (in module pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.build_actions"]], "build_observations() (in module pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.build_observations"]], "build_setting() (in module pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.build_setting"]], "build_states() (in module pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.build_states"]], "get_all_actions() (pomdp_problems.tiger.cythonize.tiger_problem.tigerpolicymodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerPolicyModel.get_all_actions"]], "get_all_observations() (pomdp_problems.tiger.cythonize.tiger_problem.tigerobservationmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel.get_all_observations"]], "get_all_states() (pomdp_problems.tiger.cythonize.tiger_problem.tigertransitionmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel.get_all_states"]], "get_distribution() (pomdp_problems.tiger.cythonize.tiger_problem.tigerobservationmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel.get_distribution"]], "get_distribution() (pomdp_problems.tiger.cythonize.tiger_problem.tigerrewardmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerRewardModel.get_distribution"]], "get_distribution() (pomdp_problems.tiger.cythonize.tiger_problem.tigertransitionmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel.get_distribution"]], "main() (in module pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.main"]], "name (pomdp_problems.tiger.cythonize.tiger_problem.tigerobservation attribute)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservation.name"]], "name (pomdp_problems.tiger.cythonize.tiger_problem.tigerstate attribute)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerState.name"]], "pomdp_problems.tiger.cythonize": [[57, "module-pomdp_problems.tiger.cythonize"]], "pomdp_problems.tiger.cythonize.tiger_problem": [[57, "module-pomdp_problems.tiger.cythonize.tiger_problem"]], "probability() (pomdp_problems.tiger.cythonize.tiger_problem.tigerobservationmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel.probability"]], "probability() (pomdp_problems.tiger.cythonize.tiger_problem.tigerpolicymodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerPolicyModel.probability"]], "probability() (pomdp_problems.tiger.cythonize.tiger_problem.tigerrewardmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerRewardModel.probability"]], "probability() (pomdp_problems.tiger.cythonize.tiger_problem.tigertransitionmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel.probability"]], "sample() (pomdp_problems.tiger.cythonize.tiger_problem.tigerobservationmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerObservationModel.sample"]], "sample() (pomdp_problems.tiger.cythonize.tiger_problem.tigerpolicymodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerPolicyModel.sample"]], "sample() (pomdp_problems.tiger.cythonize.tiger_problem.tigerrewardmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerRewardModel.sample"]], "sample() (pomdp_problems.tiger.cythonize.tiger_problem.tigertransitionmodel method)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.TigerTransitionModel.sample"]], "test_planner() (in module pomdp_problems.tiger.cythonize.tiger_problem)": [[57, "pomdp_problems.tiger.cythonize.tiger_problem.test_planner"]]}}) \ No newline at end of file