self-play 开源项目推荐（394 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

opendilab /DI-engine

OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

opendilab /LightZero

[NeurIPS 2023焦点] LightZero：一般顺序决策场景中蒙特卡罗树搜索的统一基准（令人敬畏的MCTS）

opendilab /DI-star

An artificial intelligence platform for the StarCraft II with large-scale distributed training and grand-master agents.

uclaml /SPIN

Self-Play Fine-Tuning（SPIN）

uclaml /SPPO

The official implementation of Self-Play Preference Optimization (SPPO)

inspirai /TimeChamber

A Massively Parallel Large Scale Self-Play Framework

Jaasssoooonnnnn /FirstLight_CR

Offline Clash Royale AI agent research: native simulation, imitation learning, PPO, and interactive evaluation. 离线对局模拟、模仿学习、强化学习与交互评测。

spiral-rl /spiral

SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning

Naton1 /osrs-pvp-reinforcement-learning

Train a neural network to PvP in Old School RuneScape using reinforcement learning.

halfrost /threes-ai

🏆 Threes! AI: deck-aware expectimax, N-tuple TD learning, and AlphaZero

ChuaCheowHuan /gym-continuousDoubleAuction

A custom MARL (multi-agent reinforcement learning) environment where multiple agents trade against one another (self-play) in a zero-sum continuous double auction. Ray [RLlib] is used for training.

Alibaba-Quark /SSP

Search Self-Play: Pushing the Frontier of Agent Capability without Supervision

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.

cestpasphoto /alpha-zero-general

Fast CPU AlphaZero for 2+ player board games (Catan, Splendor, Azul, Santorini, Akropolis, …). Play online in your browser.

dellalibera /gym-backgammon

Backgammon OpenAI Gym

thu-nics /MARSHAL

[ICLR'26] MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs

seungeunrho /football-paris

The exact codes used by the team "liveinparis" at the kaggle football competition ranked 6th/1141

masterai-top /cfr-poker-ai-masterai

CFR-based Heads-Up No-Limit Texas Hold'em AI – MasterAI v3.0 | 德州扑克|基于反事实遗憾最小化的德州扑克AI系统 | 强化学习 + 深度神经网络|德州俱乐部 | 源码德州AI | 德州扑克1v多博弈AI系统 | 德州AI模型，德州高级AI， 私局/大厅局/俱乐部/联盟/赛事 |德州源码，德州游戏源码，德州app源码，德州扑克app源码，德州游戏app源码，德州撲克，德撲源碼，德州源碼，德州俱樂部源碼，德州遊戲源碼，德州錦標賽，撲克源碼，HHpoker源码，百人德州，德州牛仔，ALLIN源码，AAPOKER，AAPOKER源码

dellalibera /td-gammon

TD-Gammon implementation