v2.4.0

TL;DR

• Superko rule change in Go (v0 -> v1)
• Internal refactor in Chess

What's Changed

• [Go] Use hash by @sotetsuk in #1224
• [Go] internal refactor by @sotetsuk in #1225
• [Chess] Separate Chess specific attributes by @sotetsuk in #1226
• [Chess] Extract game logic functions by @sotetsuk in #1227
• [Chess] Move game logic to _src/games by @sotetsuk in #1228
• [Chess] Add game class by @sotetsuk in #1229
• [Chess] Skip _flip in checking mate by @sotetsuk in #1230
• [Chess] Reduce _is_checked call by @sotetsuk in #1231
• [Chess] Summarize _is_checked calls by @sotetsuk in #1232
• [Chess] Enhance CAN_MOVE by @sotetsuk in #1234
• [Chess] Remove cached info by @sotetsuk in #1233
• [Chess] Simplify legal_underpromotions by @sotetsuk in #1236
• [Chess] Remove _is_pseudo_legal by @sotetsuk in #1237
• [Chess] Tidy _apply_move by @sotetsuk in #1238
• [Chess] Tidy comments by @sotetsuk in #1239
• [Chess] Simplify hash by @sotetsuk in #1235
• [Chess] Reduce lines by @sotetsuk in #1240
• [Chess] Use numpy in to_fen by @sotetsuk in #1241
• [CI] Remove type check from CI by @sotetsuk in #1244
• [Chess] Remove chess_utils.py by @sotetsuk in #1243
• [Chess] Simplify castling attributes by @sotetsuk in #1245
• [Chess] Simplify hash implementation by @sotetsuk in #1246
• [Chess] Tidy by @sotetsuk in #1247
• [Chess] Rename turn to color by @sotetsuk in #1248
• [Chess] Tidy by @sotetsuk in #1250
• [Go] Tidy by @sotetsuk in #1249
• [Chess] use from jax import lax by @sotetsuk in #1251
• [Go] Remove hash attribute by @sotetsuk in #1252

Full Changelog: v2.3.0...v2.4.0

v2.3.0

What's Changed

• [README] Enhance link to docs by @sotetsuk in #1214
• [README] Add other JAX envs by @sotetsuk in #1216
• [Animal Shogi] Dropping PAWN on the final rank is legal by @KazukiOhta in #1218
• [MinAtar] Fix svg visualization by @sotetsuk in #1219
• [AnimalShogi] Update version by @sotetsuk in #1221
• [CI] Drop py3.8 and test py3.9 by @sotetsuk in #1222
• [Release] v.2.3.0 by @sotetsuk in #1220

Full Changelog: v2.2.0...v2.3.0

v2.2.0

What's Changed

• [Animal Shogi] Modify the visualizer of animal shogi. by @KazukiOhta in #1208
• [Animal Shogi] Modify the move of GOLD in animal_shogi.py by @KazukiOhta in #1209
• Update README.md by @KazukiOhta in #1211
• [Animal Shogi] Update documents by @sotetsuk in #1212

Full Changelog: v2.1.2...v2.2.0

v2.1.2

What's Changed

• [KuhnPoker] Update docs by @sotetsuk in #1197
• [Backgammon] Fix deprecated a_min and a_max by @sotetsuk in #1201
• [LeducHoldem] suppress warnings in tests by @sotetsuk in #1202
• [MinAtar] Restore MinAtar tests by @sotetsuk in #1203
• [MinAtar] make minatar submodule by @sotetsuk in #1204
• [BridgeBidding] Update version by @sotetsuk in #1206

Full Changelog: v2.1.1...v2.1.2

v2.1.1

Upgrade KuhnPoker to v1

v2.1.0

There is a breaking change in Kuhn Poker in #1171
There are several internal changes in Go, Tic-tac-toe, and ConnectFour.

What's Changed

• [Example] Use optax policy loss by @sotetsuk in #1106
• [Example] Extract loss input computation by @sotetsuk in #1107
• [Example] Add MCTS example by @sotetsuk in #1109
• [CI] Hotfix haiku install errors by @sotetsuk in #1114
• [CI] Suppress codecov by @sotetsuk in #1110
• [CI] Simplify GitHub Action file by @sotetsuk in #1112
• [colab] Fix link to colab by @sotetsuk in #1117
• Update .gitignore by @sotetsuk in #1118
• [Docs] Add JaxMARL to README by @sotetsuk in #1120
• [CI] Fix build by @sotetsuk in #1121
• [Mahjong] Reduce compilation/run time of _pass() by @OkanoShinri in #1122
• Add XLand-MiniGrid to README by @Howuhh in #1124
• [Docs] Add notes in AZ readme by @sotetsuk in #1125
• [Tidy] Remove unnecessary comments by @sotetsuk in #1126
• [Docs] Reorder README badges by @sotetsuk in #1128
• [Go] Separate go specific attributes by @sotetsuk in #1129
• [Go] Extract game logic functions by @sotetsuk in #1130
• [Go] Move game logic to _src/games by @sotetsuk in #1131
• [Go] Refactor naming by @sotetsuk in #1132
• [Go] Add new logic class by @sotetsuk in #1133
• [Go] Use NamedTuple instead of dataclass by @sotetsuk in #1134
• [Mahjong] Add some comments for development by @OkanoShinri in #1123
• [Format] Use line_length = 120 by @sotetsuk in #1136
• [Go] Tidy by @sotetsuk in #1137
• [Go] make color optional in observe by @sotetsuk in #1138
• [Go] Fix to use history_length by @sotetsuk in #1139
• [Go] rename terminal_values to returns by @sotetsuk in #1140
• [Game API] Add __init__.py by @sotetsuk in #1142
• [Docs] UPDATE README.md by @sotetsuk in #1143
• [Protocol] Add TwoPlayerPerfectInfoGame by @sotetsuk in #1144
• [Go] Tidy signatures by @sotetsuk in #1145
• [TicTacToe] Separate TicTacToe specific attributes by @sotetsuk in #1146
• [Version] 2.1.0-rc0 by @sotetsuk in #1147
• [TicTacToe] Split game specific methods by @sotetsuk in #1148
• [TicTacToe] Extract games/tic_tac_toe.py by @sotetsuk in #1149
• [Go, TicTacToe] Align step functions by @sotetsuk in #1150
• [ConnectFour] Separate game specific attributes by @sotetsuk in #1151
• [ConnectFour] Separate game specific methods by @sotetsuk in #1152
• [ConnectFour] Extract games/connect_four.py by @sotetsuk in #1153
• [Go] Add step_count by @sotetsuk in #1155
• [Go] Move max_termination_steps to games/go.py by @sotetsuk in #1156
• [Go] Refactor using _player_order by @sotetsuk in #1157
• [Go] Fix size attribute jittable by @sotetsuk in #1158
• [Go] Tidy Go environment by @sotetsuk in #1160
• [Game] Rename returns to rewards by @sotetsuk in #1161
• [Format] Apply update black format by @sotetsuk in #1168
• Add from_fen/to_fen to pgx.experimental.chess by @sotetsuk in #1167
• [Chess] Accelerate chess_utils.py import (jnp => np) by @Akulen in #1170
• [Hotfix] Restore CI by @sotetsuk in #1175
• [Kuhn Poker] Simplify action space by @Egiob in #1171
• [README] Enhance citation information by @sotetsuk in #1181
• Bump jinja2 from 3.1.2 to 3.1.3 in /docs by @dependabot in #1182
• [Go] Extract from_sgf by @sotetsuk in #1184
• Bump jinja2 from 3.1.3 to 3.1.4 in /docs by @dependabot in #1185
• [Chess] fix dummy observation by @bkorpan in #1186
• [Bridge] Enhance DDS dataset by @sotetsuk in #1187
• Replace deprecated jax.tree_map function with jax.tree_util.tree_map by @KazukiOhta in #1188
• [CI] Remove Mahjong from CI by @sotetsuk in #1189
• Bump zipp from 3.18.0 to 3.19.1 in /docs by @dependabot in #1190
• [BridgeBidding] Improve efficiency in using dds results by @sotetsuk in #1191
• [Docs] Add https://github.com/sotetsuk/make-dds-dataset to bridge docs by @sotetsuk in #1194
• [Release] v2.1.0 by @sotetsuk in #1195

New Contributors

• @Howuhh made their first contribution in #1124
• @Akulen made their first contribution in #1170
• @Egiob made their first contribution in #1171
• @bkorpan made their first contribution in #1186
• @KazukiOhta made their first contribution in #1188

Full Changelog: v2.0.1...v2.1.0

v2.0.1

What's Changed

• [Colab] Adjust to API v2 by @sotetsuk in #1096
• [Docs] Update AlphaZero example docs by @sotetsuk in #1097
• [Example] Adjust PPO example to API v2 by @sotetsuk in #1098
• [Docs] Update AlphaZero training example docs by @sotetsuk in #1099
• [Docs] Update README by @sotetsuk in #1100
• [experimental] Add error message to auto_reset by @sotetsuk in #1102
• [experimental] Add error message to act_randomly by @sotetsuk in #1101
• [v2] Add error messages for wrong usage by @sotetsuk in #1103

Full Changelog: v2.0.0...v2.0.1

v2.0.0

API v2

Pgx has been updated from API v1 to v2 as of November 8, 2023 (release v2.0.0). As a result, the signature for Env.step has changed as follows:

• v1: step(state: State, action: Array)
• v2: step(state: State, action: Array, key: Optional[PRNGKey] = None)

Also, pgx.experimental.auto_reset are changed to specify key as the third argument.

Purpose of the update: In API v1, even in environments with stochastic state transitions, the state transitions were deterministic, determined by the _rng_key inside the state. This was intentional, with the aim of increasing reproducibility. However, when using planning algorithms in this environment, there is a risk that information about the underlying true randomness could "leak." To make it easier for users to conduct correct experiments, Env.step has been changed to explicitly specify a key.

Impact of the update: Since the key is optional, it is still possible to execute as env.step(state, action) like API v1 in deterministic environments like Go and chess, so there is no impact on these games. As of v2.0.0, only 2048, backgammon, and MinAtar suite are affected by this change.

What's Changed

• [Docs] Update 2048 version by @sotetsuk in #1036
• [Mahjong] Imprement ryuukyoku by @OkanoShinri in #1038
• [Mahjong] Imprement ron by @OkanoShinri in #1040
• Update leduc_holdem.md by @bleu48 in #1042
• [Mahjong] Imprement tsumo by @OkanoShinri in #1041
• [Mahjong] Convert to json format by @OkanoShinri in #1048
• [Backgammon] Add description to the playable_dice_count_vec by @nissymori in #1047
• [CI] Comment out some expensive tests as hotfix by @sotetsuk in #1052
• [Mahjong] Implement Menzen by @OkanoShinri in #1045
• [Mahjong] Determine current_player after pass by @OkanoShinri in #1053
• [Docs] Add license doc by @sotetsuk in #1057
• [Mahjong] Implement kandora by @OkanoShinri in #1054
• [Docs] Update citation by @sotetsuk in #1063
• [Docs] Add arXiv link by @sotetsuk in #1064
• [Mahjong] Dora-score calculation by @OkanoShinri in #1061
• [Test] Run CI with python3.10 only by @OkanoShinri in #1066
• [Colab] Update chess check by @sotetsuk in #1068
• [Mahjong] Add mahjong to Env by @OkanoShinri in #1069
• [Example] Add wandb link by @sotetsuk in #1072
• [Example] Use default Gumbel AlphaZero hyperparameters by @sotetsuk in #1055
• [API] Use int32 instead of int8/16 by @sotetsuk in #1074
• [Test] Remove redundant random play tests by @sotetsuk in #1076
• [Chess] Fix wrong zobrist hash by @sotetsuk in #1078
• [Experimental] Fix act_randomly API by @sotetsuk in #1077
• [2048] Fix bug in legal action mask by @sotetsuk in #1049
• [Mahjong] Remove old files by @sotetsuk in #1075
• [Backgammon] Update document by @sotetsuk in #1046
• [dataclass] Fix dataclass mutable defaults error by @carlosgmartin in #1067
• [dataclass] Suppress C901 by @sotetsuk in #1080
• [Mahjong] Add type annotations by @sotetsuk in #1081
• Add Python 3.11 CI by @sotetsuk in #997
• [CI] Add Python 3.12 to CI by @sotetsuk in #1082
• v2 API by @sotetsuk in #1058
• [Docs] Fix API document by @sotetsuk in #1083
• [Dependency] Update JAX version by @sotetsuk in #1084
• [Typing] Add types.py by @sotetsuk in #1085
• [dataclass] Trace Flax dataclass updates by @sotetsuk in #1086
• [Tidy] Add requirements.txt by @sotetsuk in #1087
• [experimental] Adjust auto_reset to v2 API by @sotetsuk in #1088
• [Mahjong] Add assets in release by @sotetsuk in #1089
• [MinAtar] Fix minatar usage by @sotetsuk in #1090
• [Backgammon, 2048] Update versions by @sotetsuk in #1092
• [Docs] v2 API description by @sotetsuk in #1091
• [Chess] Update version by @sotetsuk in #1093
• [2048] Update documents by @sotetsuk in #1094
• [Mahjong] Unregister mahjong due to large file size by @sotetsuk in #1095

New Contributors

• @bleu48 made their first contribution in #1042
• @carlosgmartin made their first contribution in #1067

Full Changelog: v1.4.0...v2.0.0

v1.4.0

What's Changed

• [2048] Fix reward overflow by @sotetsuk in #1034

Full Changelog: v1.3.3...v1.4.0

v.1.3.3

What's Changed

• [Docs] Add document about baseline models by @sotetsuk in #1029
• [Mahjong] Visualize game information by @OkanoShinri in #1027
• [Baseline] Update model ids by @sotetsuk in #1030
• [Docs] Add link to training example and baseline models by @sotetsuk in #1031
• [Docs] Add link to training examples in README by @sotetsuk in #1032

Full Changelog: v1.3.2...v1.3.3