5 results found Sort:

suragnair
alpha-zero-general suragnair
1.0k
3.7k
mit
112
A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4 and more
tf mcts keras gobang gomoku alphago othello pytorch alphazero self-play alpha-zero tensorflow alphago-zero deep-learning neural-network reinforcement-learning monte-carlo-tree-search
Created 2017-12-01
220 commits to master branch, last one about a month ago
pytorch
ELF pytorch
568
3.4k
other
190
ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation
go rl alpha-zero alphago-zero rl-environment reinforcement-learning
This repository has been archived (exclude archived)
Created 2018-04-26
68 commits to master branch, last one 5 years ago
huangeddie
GymGo huangeddie
31
163
unknown
4
An environment of the board game Go using OpenAI's Gym API
go mu-zero open-ai alpha-go alpha-zero open-ai-gym reinforcement-learning
Created 2019-08-26
195 commits to master branch, last one 2 years ago
richemslie
galvanise_zero richemslie
10
83
mit
11
Learning from zero (mostly based off of AlphaZero) in General Game Playing.
ggp hex baduk chess gzero amazons reversi connect6 alphazero alpha-zero breakthrough deep-learning expert-iteration general-game-playing reinforcement-learning
Created 2017-11-28
654 commits to dev branch, last one 4 years ago
ar-nowaczynski
utttai ar-nowaczynski
5
53
apache-2.0
2
AlphaZero-like AI solution for playing Ultimate Tic-Tac-Toe in the browser
ai browser alpha-zero onnxruntime ultimate-tic-tac-toe
Created 2021-12-10
30 commits to main branch, last one 2 years ago