AlphaZero back-end's RESTful APIs for Gomoku also using Cocos2d-x for front-end.

Example usage of the hometrainer library

Intelligent agents for two player games

Alpha Zero general-purpose reinforcement learning algorithm implemented for the Chess variant Racing Kings.

Simple Omok(Five in a row) game using React and ONNX.js

AlphaZeroを用いた京都将棋のゲームAI

Multi-Agent Reinforcement Learning

Experimental implementation of AlphaZero and AlphaKhan.

General Tree Evaluation for AlphaZero - MSc Thesis

Implementation of AlphaZero for playing Dots and Boxes [Python/PyTorch].

Congratulation to DeepMind! This is a reengineering implementation (on behalf of many other git repo in /support/) of DeepMind's Oct19th publication: [Mastering the Game of Go without Human Knowledge]. The supervised learning approach is more practical for individuals. (This repository has single purpose of education only)

Hex game bot powered by reinforcement learning.

Naive Implementation of AlphaZero (WIP)

A collection of combinatorial games.

A Reinforcement Learning library for solving custom environments

this is my unfinished engine. using the MCαβ algorithm.

The pbrain-Z2I is just a gomoku engine which use the protocol of gomocup. （最新权重在咸鱼有售）