Popular GitHub Repositories for Imperfect Demonstrations

OpenChat: Advancing Open-source Language Models with Imperfect Data

Awesome Game AI materials of Multi-Agent Reinforcement Learning

Scalable Implementation of Deep CFR and Single Deep CFR

[NeurIPS 2022] PerfectDou: Dominating DouDizhu with Perfect Information Distillation

CrossWeigh: Training Named Entity Tagger from Imperfect Annotations

Implementation of the paper "Overcoming Exploration in Reinforcement Learning with Demonstrations" Nair et al. over the HER baselines from OpenAI

Play, learn, solve, and analyze No-Limit Texas Hold Em. Implementation follows from Monte Carlo counter-factual regret minimization over with hierarchical K-means imperfect recall abstractions.

Foundation Model Training Using Human Demonstrations

Challenging Memory-based Deep Reinforcement Learning Agents

Reinforcement learning (RL) implementation of imperfect information game Mahjong using markov decision?processes to predict future game states

Offical code of the paper Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Learning.

Machine Learning Demonstrations: A graphical interface to draw data, apply a diverse array of machine learning tools to it, and directly see the results in a visual and understandable manner.

[ICML 2019] Implementation of "Imitation Learning from Imperfect Demonstration"

AI agents for the bavarian card game Schafkopf trained with reinforcement learning

德州扑克AI软件MasterAI，专注于多人（单人或多人）德州扑克不完全信息博弈。MasterAI 2.0版本是在MasterAI 1.0的基础上迭代改进的算法，它结合了通用的强化学习和搜索技术，在无限注德州扑克一对一游戏中实现了超越人类的表现。现出售AI源码。联系方式：Telegram：@xuzongbin001；邮箱：masterai918@gmail.com

[ICML 2022] The official implementation of DWBC in "Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations"

Generate expert demonstrations; GAIL(Generative Adversarial Imitation Learning); IRL(Inverse Reinforcement Learning)

AI algorithm that plays Texas hold 'em poker (part of university research in imperfect information games)

[ICML 2021] Learning to Weight Imperfect Demonstrations

MasterAI is an AI poker dedicated to suport n-play (single- or multi-agent) Texas Hold'em imperfect-informatin games.