alpha-zero 开源项目推荐（50 个）

suragnair /alpha-zero-general

基于AlphaZero的干净实现，适用于任何框架中的任何游戏+教程+ Othello/Gobang/TicTacToe/Connect 4等

pytorch /ELF

ELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation

huangeddie /GymGo

An environment of the board game Go using OpenAI's Gym API

blanyal /alpha-zero

AlphaZero implementation for Othello, Connect-Four and Tic-Tac-Toe based on "Mastering the game of Go without human knowledge" and "Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm" by DeepMind.

richemslie /galvanise_zero

Learning from zero (mostly based off of AlphaZero) in General Game Playing.

arnowaczynski /utttai

AlphaZero-like AI solution for playing Ultimate Tic-Tac-Toe in the browser

tejank10 /AlphaGo.jl

AlphaGo Zero implementation using Flux.jl

sirmammingtonham /alphastone

Using self-play, MCTS, and a deep neural network to create a hearthstone ai player

AIRLegend /ChessRL

Deep Reinforcement Learning for Chess

kongjiellx /AlphaZero-Renju

该项目在 GitHub 上没有填写描述

jianzhnie /RLZero

A clean and easy implementation of MuZero, AlphaZero and Self-Play reinforcement learning algorithms for any game.

yangrc1234 /Gomoku-Zero

A gomoku AI based on Alpha Zero paper.

peldszus /alpha-zero-general-lib

An implementation of the AlphaZero algorithm for adversarial games to be used with the machine learning framework of your choice

psiorx /Reinforcement-Learning

Simple C++ project that includes header only implementations of Monte Carlo Tree Search(MCTS), Temporal Difference Learning, Minimax, and other agents to evaluate their performance in various two player games. Also includes an implementation of AlphaZero for Connect4.

MerceaOtniel /HybridAlpha

HybridAlpha - a mix between AlphaGo Zero and AlphaZero for multiple games

PlanetMoon /TwelveShogi_AlphaZero

A simplified version of Shogi with the AI is trained by alpha-zero-type training method

0xNineteen /hyper-alpha-zero

hyper optimized alpha zero implementation to play gomoku (distributed training with ray, mcts with cython)

mathemage /AlphaZero-presentation

presentation on AlphaZero for AI seminar (http://ktiml.mff.cuni.cz/~bartak/ui_seminar/)

JernejHabjan /TrumpDefense2020

Visual representation of RTS game, supported by deep reinforcement learning algorithm Alpha Zero written in python.

evolutionsoftswiss /alpha-zero-learning

Java based alpha zero reinforcement learning. The core module suppports implementing any adversary board game. Example implementation for Tic Tac Toe.