Deep Reinforcement Learning in Rust

Overview

This project implements a collection of Deep Reinforcement Learning (DRL) algorithms in Rust.
It provides a modular architecture for training, evaluating, and comparing various model-based and model-free methods across several custom environments.

---

Features

✅ Implemented Algorithms

Model-Based:

• Expert Apprentice
• Monte Carlo

Model-Free:

• Proximal Policy Optimization (PPO)
• Q-Learning
• REINFORCE
• SARSA

🌍 Environments

• Line World
• Grid World
• Tic-Tac-Toe
• Bobail (African traditional game)

---

Requirements

• Rust (Stable)
• CUDA (Optional, for GPU acceleration)
• Ensure libtorch environment variables are properly configured if using CUDA

---

Installation

1. Clone the repository:

   git clone https://github.com/your-username/deep-rl-rust.git
   cd deep-rl-rust

2. Build the project:

   cargo build --release

---

Usage

Run the project with:

cargo run --release

Configure algorithm/environment via code or future CLI options.

---

Contributions

Contributions are welcome!
Feel free to fork the repo, suggest improvements, or submit a pull request.

---

License

This project is licensed under the MIT License.
See the LICENSE file for details.

---

🚀 Happy Reinforcement Learning!