jonathan-laurent/AlphaZero.jl
A generic, simple and fast implementation of Deepmind's AlphaZero algorithm.
Built in Julia for 1-2 orders of magnitude faster execution than pure Python alternatives, it combines Monte Carlo tree search with neural networks trained through self-play. Generic interfaces support arbitrary games and learning frameworks, while distributed training across machine clusters requires no code modifications—enabling meaningful experiments on standard desktop hardware with modest GPUs.
1,312 stars.
Stars
1,312
Forks
147
Language
Julia
License
MIT
Category
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.
Related frameworks
mokemokechicken/reversi-alpha-zero
Reversi reinforcement learning by AlphaGo Zero methods.
NeymarL/ChineseChess-AlphaZero
Implement AlphaZero/AlphaGo Zero methods on Chinese chess.
werner-duvaud/muzero-general
MuZero
suragnair/alpha-zero-general
A clean implementation based on AlphaZero for any game in any framework + tutorial +...
DHDev0/Stochastic-muzero
Pytorch Implementation of Stochastic MuZero for gym environment. This algorithm is capable of...