UNO Card Game with Reinforcement Learning๏ƒ

Welcome to the documentation for the UNO Card Game RL project! This project implements a complete UNO card game with multiple Reinforcement Learning agents.

https://img.shields.io/badge/python-3.8+-blue.svg https://img.shields.io/badge/license-MIT-green.svg

Overview๏ƒ

This project explores the application of Reinforcement Learning to the classic UNO card game. Our agents achieve 60%+ win rates against random opponents, with our Self-Play Champion targeting 70%+ win rates.

Key Features๏ƒ

  • ๐Ÿƒ Complete UNO Engine: Full game rules including special cards

  • ๐Ÿค– Multiple RL Agents: Q-Learning, DQN, PPO, Recurrent PPO

  • ๐ŸŽฎ Modern GUIs: Pygame-based interfaces with glassmorphism design

  • ๐Ÿ‘ฅ Multiplayer Support: 2-4 player battles

  • ๐Ÿ“Š Model Comparison: Evaluate and compare different agents

  • ๐Ÿ”„ Self-Play Training: Train agents against themselves

Quick Start๏ƒ

# Clone repository
git clone https://github.com/user/uno-card-game-rl.git
cd uno-card-game-rl

# Install dependencies
pip install -r requirements.txt

# Play against AI
python uno_gui.py

# Watch AI battles
python model_battle_gui.py

Table of Contents๏ƒ

Reference

Indices and tables๏ƒ