Game Playing AlphaZero ML Frameworks

Implementations and educational resources for AlphaZero and its variants applied to board games and game environments. Includes complete algorithm implementations, game-specific adaptations, and explanatory materials. Does NOT include general reinforcement learning frameworks, other game-playing algorithms (MCTS-only, Q-learning), or non-game applications of these techniques.

There are 43 game playing alphazero frameworks tracked. 6 score above 50 (established tier). The highest-rated is jonathan-laurent/AlphaZero.jl at 53/100 with 1,312 stars.

Get all 43 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=ml-frameworks&subcategory=game-playing-alphazero&limit=20"

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

#	Framework	Score	Tier	Stars	Language
1	jonathan-laurent/AlphaZero.jl A generic, simple and fast implementation of Deepmind's AlphaZero algorithm.	53	Established	1,312	Julia
2	suragnair/alpha-zero-general A clean implementation based on AlphaZero for any game in any framework +...	51	Established	4,388	Jupyter Notebook
3	NeymarL/ChineseChess-AlphaZero Implement AlphaZero/AlphaGo Zero methods on Chinese chess.	51	Established	1,205	Python
4	mokemokechicken/reversi-alpha-zero Reversi reinforcement learning by AlphaGo Zero methods.	51	Established	686	Python
5	werner-duvaud/muzero-general MuZero	51	Established	2,784	Python
6	donkirkby/zero-play Teach a computer to play any game.	50	Established	10	Python
7	DHDev0/Stochastic-muzero Pytorch Implementation of Stochastic MuZero for gym environment. This...	47	Emerging	77	Python
8	JohnLyu2/z3alpha Synthesizes efficient Z3 strategies tailored to your problem set! Repo for...	47	Emerging	23	Python
9	bhansconnect/alphazero-pybind11 A modified Alphazero implementation with C++ where performance matters.	47	Emerging	18	C++
10	kevaday/alphazero-general A fast, generalized, and modified implementation of Deepmind's distinguished...	46	Emerging	87	Python
11	kaesve/muzero A clean implementation of MuZero and AlphaZero following the AlphaZero...	44	Emerging	168	Jupyter Notebook
12	maxpumperla/ScalphaGoZero An independent implementation of DeepMind's AlphaGoZero in Scala, using...	44	Emerging	156	Scala
13	maxpumperla/deep_learning_and_the_game_of_go Code and other material for the book "Deep Learning and the Game of Go"	43	Emerging	1,051	Python
14	kobanium/TamaGo Computer go engine using Monte-Carlo Tree Search written in Python3.	43	Emerging	71	Python
15	tomwhite/set-game Play SET using image recognition and deep learning	42	Emerging	29	Java
16	CGLemon/pyDLGO 基於深度學習的 GTP 圍棋（围棋）引擎，KGS 指引文件以及演算法教學。	41	Emerging	69	Python
17	tuero/muzero-cpp A C++ pytorch implementation of MuZero	40	Emerging	40	C++
18	YoujiaZhang/AlphaGo-Zero-Gobang AlphaGo-Zero-Gobang 是一个基于强化学习的五子棋(Gobang)模型，主要用以了解AlphaGo...	39	Emerging	110	Python
19	Hwhitetooth/jax_muzero An implementation of MuZero in JAX.	39	Emerging	57	Python
20	markhliu/AlphaGoSimplified Book repository for AlphaGo Simplified (CRC Press 2024). Implement ideas...	39	Emerging	34	Jupyter Notebook
21	marchete/CGZero AlphaZero like implementation for Oware Abapa game	39	Emerging	26	C++
22	XUNIK8/Reinforcement-Learning-in-Tsumego 利用强化学习、基于蒙特卡洛树搜索的UCT算法解决围棋死活题问题。Inplement improved Reinforcement Learning...	36	Emerging	15	Python
23	DHDev0/Muzero-unplugged Pytorch Implementation of MuZero Unplugged for gym environment. This...	36	Emerging	35	Python
24	zjeffer/chess-deep-rl-cpp C++ version of my chess-deep-rl project. WIP	35	Emerging	7	C++
25	DHDev0/Muzero Pytorch Implementation of MuZero for gym environment. It support any...	34	Emerging	19	Python
26	mathemage/AlphaZero-presentation presentation on AlphaZero for AI seminar...	33	Emerging	7	TeX
27	andreaslam/ZanLing-TrueZero A Python and Rust chess engine that starts from Zero.	32	Emerging	6	Python
28	MichiganDataScienceTeam/W25-mini-alphago AlphaGo for 9x9 Go from scratch	30	Emerging	10	Python
29	wangjia184/renju A Reinforcement-Learning based Renju game	29	Experimental	9	C++
30	JernejHabjan/TrumpDefense2020 Visual representation of RTS game, supported by deep reinforcement learning...	29	Experimental	7	C++
31	Joker2770/Z2I The pbrain-Z2I is just a gomoku engine which use the protocol of gomocup. （最新权重在咸鱼有售）	29	Experimental	4	C++
32	MSI-DEV/muzero-general MuZero	22	Experimental	—	Python
33	ColorDiff/alphazero Complete implementation of the AlphaZero algorithm	22	Experimental	6	Python
34	p3achyjr/p3achygo (Yet Another) AlphaZero-based Go Engine	22	Experimental	5	C++
35	tachyon-beep/keisei A Deep Reinforcement Learning project demonstrating AI's power to create AI,...	21	Experimental	—	Python
36	grimmlab/SynGameZero SynGameZero – Flowsheet Synthesis in a Game environment with Zero Knowledge	20	Experimental	5	—
37	BIGBALLON/Toward-AGZ Materials for AlphaGo	19	Experimental	4	—
38	RealClearwave/NeoRenju An AI Renju Engine Using Tensorflow, Pytorch and Ffmpeg	19	Experimental	3	C++
39	SemanticWave-Hoyeon/ReinforcementRenju A GPU-accelerated AlphaZero implementation for Renju (Gomoku/Five-in-a-Row)...	19	Experimental	—	Python
40	mcfarljm/dlchess AlphaZero for chess, from scratch	18	Experimental	2	C++
41	alexZajac/muzero_experiments A set of experiments and human-playing comparisons with the Muzero agent...	17	Experimental	1	Python
42	navreeetkaur/AlphaGoZero Implementation of Alpha Go Zero - Reinforcement Learning Project, COL870 @iit-delhi	12	Experimental	6	Python
43	WNoxchi/alphazero_prev Experimental implementation of AlphaZero and AlphaKhan.	11	Experimental	—	Jupyter Notebook

Comparisons in this category

reversi-alpha-zero and alpha-zero-general (51 vs 51) alpha-zero-general and AlphaGo-Zero-Gobang (51 vs 39) alpha-zero-general and alphazero-general (51 vs 46) muzero-general and muzero (51 vs 44) muzero-general and muzero-cpp (51 vs 40) reversi-alpha-zero and ChineseChess-AlphaZero (51 vs 51) AlphaZero.jl and alphazero-general (53 vs 46) ChineseChess-AlphaZero and AlphaGo-Zero-Gobang (51 vs 39)