Skip to content

Latest commit

 

History

History
59 lines (37 loc) · 2.83 KB

File metadata and controls

59 lines (37 loc) · 2.83 KB

Atari Games Deep Reinforcement Learning

License Stable Baselines PyTorch OpenAI Gym

This repository is a comprehensive resource for Deep Reinforcement Learning (RL) enthusiasts looking to delve into the world of Atari gaming environments. Through a collection of Jupyter notebooks, I demonstrate the application of various state-of-the-art RL algorithms to tackle Atari games, providing both beginners and seasoned practitioners with valuable insights and practical examples.

Pong Environment

Key Features

  • Diverse Algorithms: Explore the training processes of popular Deep RL algorithms, including Proximal Policy Optimization (PPO), Deep Deterministic Policy Gradient (DDPG), Deep Q-Networks (DQN), Advantage Actor-Critic (A2C), and more.

  • Gymnasium Environments: Utilize OpenAI's Gymnasium environments to simulate Atari games, offering a standardized platform for RL experimentation. Gymnasium Documentation

  • Stable Baselines 3: Implement RL algorithms with ease using Stable Baselines 3, a powerful library built on top of PyTorch. Stable Baseline3 Documentation

Table of Contents

Installation

  1. Clone the repository:
    git clone https://github.com/bantu-4879/Atari_Games-Deep_Reinforcement_Learning.git
  2. Install the required dependencies:
    pip install -r requirements.txt

Usage

Navigate to the notebooks directory and open any desired Jupyter notebook to explore the training procedures of different RL algorithms on Atari games.

Contributing

Contributions are welcome! Feel free to open issues or pull requests to suggest improvements, report bugs, or add new features.

License

This project is licensed under the MIT License.

Special Thanks

A special thanks to Thomas Simonini for the inspiration and valuable insights that contributed to the development of this repository.

Acknowledgments

This repository was inspired by and learned from Deep Reinforcement Learning Class.