Anroshka/snake-ai

🐍 A Snake game AI that learns to play through Deep Q-Learning. Built with PyTorch and Pygame, featuring CUDA acceleration and real-time visualization of the learning process.

28
/ 100
Experimental

This project helps machine learning engineers and researchers explore and visualize deep reinforcement learning concepts by training AI agents to play the classic Snake game. It takes in game state information and outputs trained AI models that can play Snake intelligently, along with real-time visualizations of the learning process. This is ideal for those learning about or experimenting with Deep Q-Learning.

Use this if you are a machine learning practitioner looking for a hands-on, visualized environment to understand and experiment with Deep Q-Learning, especially with multi-agent scenarios.

Not ideal if you are looking for a pre-built, production-ready AI for a different game or a general-purpose reinforcement learning framework without a game-specific context.

deep-reinforcement-learning q-learning multi-agent-systems ai-training educational-tool
No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

Python

License

MIT

Category

snake-game-ai

Last pushed

Nov 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Anroshka/snake-ai"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.