self-play repositories
Trending repositories tagged self-play, ranked by trending score. Updated daily.
-
1
Jaasssoooonnnnn/FirstLight_CR
Offline Clash Royale AI research: native simulation, imitation learning, PPO, and interactive evaluation.
GitHub · Python · 340 stars · 85 forks · +207 stars in 24 hours · Trending score 4.13
-
2
RobinKa/warcraftsim
Headless Warcraft III (Legacy TFT 1.29) under Wine for reinforcement learning: the real game stepped from Python, with PufferLib 5 training, behavior cloning and a training dashboard.
GitHub · Python · 35 stars · 2 forks · +2 stars in 24 hours · Trending score 1.02
-
3
Jaasssoooonnnnn/FirstLight-Zero
AlphaZero-style self-play Clash Royale. It beats a human-data imitation model
GitHub · Python · 20 stars · 3 forks · 0 stars in 24 hours · Trending score 0.32
-
4
will-rice/llm-self-improvement-papers
Research papers on LLM self-improvement: self-training, self-refinement, self-play, self-rewarding, and self-evolving language models
GitHub · Python · 6 stars · 0 forks · 0 stars in 24 hours · Trending score 0.09
-
5
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.
GitHub · Python · 155 stars · 33 forks · 0 stars in 24 hours · Trending score 0.01
-
6
deeptexas-ai/deep-holdem-ai
HUNL德州扑克AI源码:CFR子博弈、ReBeL递归求解、反事实价值网络、自博弈与C++蒙特卡洛 | Texas Hold'em AI research
GitHub · C++ · 33 stars · 8 forks · 0 stars in 24 hours · Trending score 0.00
-
7
masterai-top/cfr-poker-ai-masterai
德州AI源码与CFR扑克研究:C++/Python、HUNL、自我博弈、反事实价值、策略训练与离线评估。Texas Holdem Poker AI source code.
GitHub · C++ · 55 stars · 22 forks · 0 stars in 24 hours · Trending score 0.00
-
8
masterai-top/TexasHoldem-Poker-AI-HeadsUp-Engine
德州AI源码与CFR算法引擎:C/C++德州扑克机器人,包含自我博弈、强化学习、牌力评估与实时决策 | Texas Hold'em AI source code and CFR poker bot
GitHub · C++ · 29 stars · 10 forks · 0 stars in 24 hours · Trending score 0.00
-
9
lucidrains/self-play-pretrain-zero-data
Implementation of Self-Play Pretraining with Zero Data
GitHub · Python · 10 stars · 1 forks · 0 stars in 24 hours · Trending score 0.00
-
10
tommy85/MirrorForce
Yu-Gi-Oh! (YGO) AI trained by self-play reinforcement learning on the YGOPro engine; champion of the first YGO agent competition
GitHub · Python · 11 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00
-
11
illuin-tech/daedalus
DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks. Code, paper and blog post.
GitHub · Python · 11 stars · 0 forks · 0 stars in 24 hours · Trending score 0.00