suragnair/alpha-zero-general
A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more
This project offers a flexible implementation of the AlphaZero algorithm, enabling you to train an AI to play any two-player turn-based board game. It takes the rules of a game and a neural network model as input, and outputs a highly skilled AI player that learns through self-play. This is ideal for AI researchers, game designers, or hobbyists looking to create strong AI opponents for custom or existing board games.
4,388 stars. No commits in the last 6 months.
Use this if you want to develop an AI player for a two-player turn-based game that learns optimally without human expert data.
Not ideal if you need an AI for real-time strategy games, single-player games, or games with imperfect information.
Stars
4,388
Forks
1,147
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jan 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/suragnair/alpha-zero-general"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
jonathan-laurent/AlphaZero.jl
A generic, simple and fast implementation of Deepmind's AlphaZero algorithm.
NeymarL/ChineseChess-AlphaZero
Implement AlphaZero/AlphaGo Zero methods on Chinese chess.
werner-duvaud/muzero-general
MuZero
mokemokechicken/reversi-alpha-zero
Reversi reinforcement learning by AlphaGo Zero methods.
donkirkby/zero-play
Teach a computer to play any game.