donkirkby/zero-play
Teach a computer to play any game.
Zero Play helps game developers and AI researchers create powerful computer opponents for board games. You provide the rules of your game, and the system trains an AI to play it, even without prior game knowledge. The output is a highly skilled AI player that can be integrated into your game or used for research into game AI.
Available on PyPI.
Use this if you need to build a robust, self-learning AI opponent for a new or existing board game and want to leverage modern AI techniques.
Not ideal if you're looking for pre-built AI for common commercial games or a drag-and-drop tool without any coding.
Stars
10
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 19, 2026
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/donkirkby/zero-play"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
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.
suragnair/alpha-zero-general
A clean implementation based on AlphaZero for any game in any framework + tutorial +...
werner-duvaud/muzero-general
MuZero
mokemokechicken/reversi-alpha-zero
Reversi reinforcement learning by AlphaGo Zero methods.