kevaday/alphazero-general

[IEEE ToG] MiniZero: An AlphaZero and MuZero Training Framework

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

A generic, simple and fast implementation of Deepmind's AlphaZero algorithm.

fast + parallel AlphaZero in JAX

[ICML 2021] DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning | 斗地主AI

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)

Board game AI implementations using Monte Carlo Tree Search

Monte Carlo tree search in JAX

Ultimate SFighterAI