thuxugang / Doudizhu
AI斗地主
Stars: ✭ 149
Programming Languages
python
139335 projects - #7 most used programming language
Projects that are alternatives of or similar to Doudizhu
Snake Ai Reinforcement
AI for Snake game trained from pixels using Deep Reinforcement Learning (DQN).
Stars: ✭ 123 (-17.45%)
Mutual labels: ai, reinforcement-learning, dqn
Aigames
use AI to play some games.
Stars: ✭ 422 (+183.22%)
Mutual labels: ai, reinforcement-learning, dqn
Atari
AI research environment for the Atari 2600 games 🤖.
Stars: ✭ 174 (+16.78%)
Mutual labels: ai, reinforcement-learning, dqn
Cartpole
OpenAI's cartpole env solver.
Stars: ✭ 107 (-28.19%)
Mutual labels: ai, reinforcement-learning, dqn
Openaigym
Solving OpenAI Gym problems.
Stars: ✭ 98 (-34.23%)
Mutual labels: reinforcement-learning, dqn
Machin
Reinforcement learning library(framework) designed for PyTorch, implements DQN, DDPG, A2C, PPO, SAC, MADDPG, A3C, APEX, IMPALA ...
Stars: ✭ 145 (-2.68%)
Mutual labels: reinforcement-learning, dqn
Torchrl
Highly Modular and Scalable Reinforcement Learning
Stars: ✭ 102 (-31.54%)
Mutual labels: reinforcement-learning, dqn
Allenact
An open source framework for research in Embodied-AI from AI2.
Stars: ✭ 144 (-3.36%)
Mutual labels: ai, reinforcement-learning
Reinforcement learning
Reinforcement learning tutorials
Stars: ✭ 82 (-44.97%)
Mutual labels: reinforcement-learning, dqn
Reinforcement Learning
🤖 Implements of Reinforcement Learning algorithms.
Stars: ✭ 104 (-30.2%)
Mutual labels: reinforcement-learning, dqn
Minimalrl
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
Stars: ✭ 2,051 (+1276.51%)
Mutual labels: reinforcement-learning, dqn
Categorical Dqn
A working implementation of the Categorical DQN (Distributional RL).
Stars: ✭ 90 (-39.6%)
Mutual labels: reinforcement-learning, dqn
Torchrl
Pytorch Implementation of Reinforcement Learning Algorithms ( Soft Actor Critic(SAC)/ DDPG / TD3 /DQN / A2C/ PPO / TRPO)
Stars: ✭ 90 (-39.6%)
Mutual labels: reinforcement-learning, dqn
Reinforcement learning
강화학습에 대한 기본적인 알고리즘 구현
Stars: ✭ 100 (-32.89%)
Mutual labels: reinforcement-learning, dqn
Reinforcement Learning Wechat Jump
Reinforcement Learning for WeChat Jump
Stars: ✭ 85 (-42.95%)
Mutual labels: ai, reinforcement-learning
Easy Rl
强化学习中文教程，在线阅读地址：https://datawhalechina.github.io/easy-rl/
Stars: ✭ 3,004 (+1916.11%)
Mutual labels: reinforcement-learning, dqn
Deep Neuroevolution
Deep Neuroevolution
Stars: ✭ 1,526 (+924.16%)
Mutual labels: ai, reinforcement-learning
Ctc Executioner
Master Thesis: Limit order placement with Reinforcement Learning
Stars: ✭ 112 (-24.83%)
Mutual labels: reinforcement-learning, dqn
Rainbow
A PyTorch implementation of Rainbow DQN agent
Stars: ✭ 147 (-1.34%)
Mutual labels: reinforcement-learning, dqn
Holodeck Engine
High Fidelity Simulator for Reinforcement Learning and Robotics Research.
Stars: ✭ 48 (-67.79%)
Mutual labels: ai, reinforcement-learning
斗地主
deecamp斗地主
master分支
提供了可以结合AI的程序引擎，在next_moves中提供按照规则的出牌所有可能性，需要自己实现从next_moves中选择所出的牌（myutil中的choose方法），默认random
web分支
1.页面展示，提供可视化调试方法
2.可以选择跟人对战
使用方法
1.启动server.py
2.访问http://127.0.0.1:5000/ddz
rl_pdqn分支
模仿OpenAI，提供了可以结合RL的程序引擎，可以选择对手为random或陈潇规则(cxgz)或自身(self)，但是训练时只能训练一个且为player 1。该分支rl模型为prioritized_dqn，具体模型参考https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow 。
目前胜率 vs random（90%）， cxgz（44%）
multi-rl分支
模仿OpenAI，提供了可以结合RL的程序引擎，可以同时训练多个rl player
mcts分支
mcts暴力解决（TODO：由于deepcopy牌局的回复速度比较慢，1000/6s）
contributor
Deecamp第五组
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].