munanfan / Mahjong_Game_RLCard_RL
基于RLCard平台的麻将mahjong博弈游戏代码,包括基于规则和基于Dueling DQN的Agent模型。
☆30Updated 3 years ago
Alternatives and similar repositories for Mahjong_Game_RLCard_RL
Users that are interested in Mahjong_Game_RLCard_RL are comparing it to the libraries listed below
Sorting:
- ☆45Updated 2 years ago
- ☆33Updated 7 months ago
- MahjongZero: DouZero for Mahjong | 麻将AI☆28Updated 2 years ago
- A Doudizhu reinforcement learning AI☆29Updated 4 months ago
- Douzero with ResNet and GPU support for Windows☆41Updated 3 years ago
- 自制麻将AI框架☆33Updated 7 years ago
- [NeurIPS 2022] PerfectDou: Dominating DouDizhu with Perfect Information Distillation☆182Updated last year
- C++版日麻. Japanese Riichi Mahjong written in C++.☆113Updated 4 months ago
- A solo 2D graphics Mahjong Game using pygame. 单机2D麻将游戏,国标麻将规则,pygame 开发☆18Updated last year
- 强化学习训练斗地主 / doudizhu AI using reinforcement learning.☆15Updated 5 years ago
- Deep reinforcement learning of mahjong self-play☆17Updated 6 years ago
- ☆43Updated last year
- 麻将AI算法(包含全概率估算、局部概率估算、深度学习版本)☆241Updated 6 years ago
- Python Fan calculator for Chinese Standard Mahjong☆20Updated 3 months ago
- Reinforcement learning (RL) implementation of imperfect information game Mahjong using markov decision processes to predict future game s…☆89Updated 2 years ago
- ☆21Updated 2 years ago
- 使用Muzero算法进行中国象棋对弈☆9Updated 4 years ago
- mcc_second_guandan☆80Updated 2 years ago
- An unoffical implementation of AlphaHoldem. 1v1 nl-holdem AI.☆87Updated last year
- 麻将胡牌算法以及AI算法☆442Updated 2 years ago
- 基于权重的斗地主游戏AI算法,AI algorithms for chinese landlord card game, based on weights☆314Updated 5 years ago
- Japanese Riichi Mahjong AI agent. (Feel free to extend this agent or develop your own agent)☆439Updated 6 years ago
- ☆13Updated 3 years ago
- ☆9Updated 2 years ago
- 国标麻将小助手——包含算番器、线下实麻计分器、番种详细说明、牌理等☆139Updated 2 weeks ago
- 中国象棋alpha zero程序☆401Updated 6 years ago
- Utility tools for tenhou.net log☆28Updated last year
- C++/python fight the lord with pybind11 (强化学习AI斗地主), Accepted to AIIDE-2020☆160Updated 3 years ago
- Leaderboard and Visualization for RLCard☆382Updated last year
- 该论文主要介绍了美国卡内基梅隆大学团队,在多人德州扑克上的人工智能新思路,即不再简单寻找纳什均衡,而引入悔恨值的概念,自我博弈,并采用蒙特卡洛CFR方法,构建蓝图,该方法通用性强,该团队声称他们的德州扑克蓝图只在两枚CPU运算8天即可得出蓝图,即可以实现实时博弈。现已经有国…☆26Updated 5 years ago