PacManAI

Welcome to PacManAI, where the timeless arcade classic meets modern artificial intelligence. My project is at the forefront of developing sophisticated AI agents capable of navigating the mazes and challenges of Pac-Man with unparalleled strategy and skill.

Features

• Multiple AI Agents: Offering a variety of AI players, each equipped with unique strategies and learning capabilities.
• NEAT Configurations: Utilizing NeuroEvolution of Augmenting Topologies (NEAT) to evolve adaptive neural networks for gameplay.
• Advanced Learning Models: Incorporating cutting-edge deep reinforcement learning techniques such as DQN and CoDeepNEAT.
• Modular Design: Our codebase is designed for extensibility, allowing for the easy integration of new AI models and gaming environments.
• Replay and Analysis: Save and review gameplay to analyze AI behavior and strategy evolution.

Getting Started

Clone the repository and install the necessary dependencies to get started with PacManAI.

# Clone the repository
git clone [repository-url]

# Navigate to the repository directory
cd PacManAI

# Install dependencies
pip install -r requirements.txt

Usage

Execute the AI agent of your choice by running the corresponding module with the desired configuration file.

# Run an AI agent
python -m ai.neat_py --config_file [path-to-config-file]

Note: Replace [path-to-config-file] with the actual path to the NEAT configuration file you wish to use.

Contributing

Your contributions are welcome! If you have ideas on how to improve PacManAI, please fork the repository, make your changes, and submit a pull request. You can also open an issue for discussion.

License

Distributed under the MIT License. See LICENSE for more information.

Contact

Project Link: [repository-url]