Experiments with Dyna-Q
-
Updated
Jul 29, 2024 - Jupyter Notebook
Experiments with Dyna-Q
Reinforcement Learning: Modification of Q-learning through the use DynaQ learning and Double-Q learning.
Reinforcement Learning Algorithms in a simple Gridworld
path planning using Q learning algorithm
ReLAx - Reinforcement Learning Applications Library
Programming assignments completed for my Reinforcement Learning course: Topics include Bandit Algorithms, Dynamic Programming, policy iteration, Monte-Carlo methods, SARSA, Q-Learning, Dyna-Q/Dyna-Q+, gradient control methods, state aggregation methods, and Deep Q-Learning Networks (DQNs).
Example DYNA-Q implementation with ReLAx
Reinforcement Learning Specialization courses solutions
Reinforcement Learning Using Q-learning, Double Q-learning, and Dyna-Q.
Solving Markov Decision Process using Value Iteration and Policy Iteration, SARSA, Expected SARSA and Q-Learning
Various fundamental reinforcement learning algorithms implemented from scratch
Reinforcement learning algorithms to solve OpenAI gym environments
Reinforcement Learning For Dialogue Systems 强化学习在对话系统中的应用 论文或开源应用总结
Assignments and Reading Material for RL Course
PyTorch implementation of various reinforcement learning algorithms
Implementation of Dyna-Q with priority sweeping on a basic n by n gridworld
Add a description, image, and links to the dyna-q topic page so that developers can more easily learn about it.
To associate your repository with the dyna-q topic, visit your repo's landing page and select "manage topics."