This repository contains a collection of Python implementations and Jupyter Notebooks that demonstrate various reinforcement learning (RL) algorithms and concepts. Each example is designed to provide a clear and practical understanding of RL techniques.
Taxi Driver: Implementation of the Taxi Driver problem using reinforcement learning.
Gym and PettingZoo Introduction: Introduction to OpenAI's Gym and PettingZoo libraries for RL environments.
Tic-Tac-Toe with Minimax: Implementation of the Minimax algorithm for playing Tic-Tac-Toe.
Q-Learning in Python: Basic implementation of the Q-Learning algorithm.
Taxi Q-Learning: Applying Q-Learning to the Taxi problem.
SARSA in Python: Implementation of the SARSA (State-Action-Reward-State-Action) algorithm.
Cliff Walking with SARSA and Q-Learning: Comparison of SARSA and Q-Learning on the Cliff Walking problem.
FrozenLake: Solving the FrozenLake environment using RL techniques.
MountainCar: Applying reinforcement learning to the MountainCar environment.
Stable-Baselines3: Examples of using the Stable-Baselines3 library for RL.
TensorBoard Integration: Using TensorBoard for visualization of RL training metrics.
To complement the code examples, a series of video tutorials has been created to provide in-depth explanations and demonstrations of the reinforcement learning concepts covered in this repository. You can access the full playlist on YouTube:
AI Reinforcement Learning Course Playlist
These videos are designed to help you better understand the implementation details and theoretical aspects of each example.
Contributions are welcome! If you have an example or improvement to share, please fork the repository, make your changes, and submit a pull request.