jonathan-laurent/AlphaZero.jl

A generic, simple and fast implementation of Deepmind's AlphaZero algorithm.

53
/ 100
Established

This tool helps researchers, students, and 'hackers' explore and apply advanced AI game-playing techniques. You input a game's rules and structure, and it trains an AI agent through self-play, producing a highly skilled AI for that game, capable of reaching superhuman performance in complex environments like Chess or Go. It's designed for those who want to understand and experiment with AI decision-making.

1,312 stars.

Use this if you are a researcher, student, or enthusiast looking to train powerful AI agents for complex games or combinatorial problems on a standard desktop computer with a GPU.

Not ideal if you need an out-of-the-box solution for a specific game without any setup or coding, or if you require an enterprise-level, highly optimized C++ implementation for massive distributed computing.

AI-research game-AI reinforcement-learning combinatorial-optimization computational-game-theory
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

1,312

Forks

147

Language

Julia

License

MIT

Last pushed

Dec 12, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jonathan-laurent/AlphaZero.jl"

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