RLCard: A Toolkit for Reinforcement Learning in Card Games

RLCard is a toolkit for Reinforcement Learning (RL) in card games. It supports multiple card environments with easy-to-use interfaces. The goal of RLCard is to bridge reinforcement learning and imperfect information games, and push forward the research of reinforcement learning in domains with multiple agents, large state and action space, and sparse reward. RLCard is developed by DATA Lab at Texas A&M University.

Official Website: http://www.rlcard.org
Paper: https://arxiv.org/abs/1910.04376

Installation

Make sure that you have Python 3.5+ and pip installed. We recommend installing rlcard with pip as follow:

git clone https://github.com/datamllab/rlcard.git
cd rlcard
pip install -e .

Or you can directly install the package with

pip install rlcard

Examples

Please refer to examples/. A short example is as below.

import rlcard
from rlcard.agents.random_agent import RandomAgent

env = rlcard.make('blackjack')
env.set_agents([RandomAgent()])

trajectories, payoffs = env.run()

We also recommend the following toy examples.

Demo

Run examples/leduc_holdem_human.py to play with the pre-trained Leduc Hold'em model. Leduc Hold'em is a simplified version of Texas Hold'em. Rules can be found here.

>> Leduc Hold'em pre-trained model

>> Start a new game!
>> Agent 1 chooses raise

=============== Community Card ===============
┌─────────┐
│░░░░░░░░░│
│░░░░░░░░░│
│░░░░░░░░░│
│░░░░░░░░░│
│░░░░░░░░░│
│░░░░░░░░░│
│░░░░░░░░░│
└─────────┘
===============   Your Hand    ===============
┌─────────┐
│J        │
│         │
│         │
│    ♥    │
│         │
│         │
│        J│
└─────────┘
===============     Chips      ===============
Yours:   +
Agent 1: +++
=========== Actions You Can Choose ===========
0: call, 1: raise, 2: fold

>> You choose action (integer):

Documents

Please refer to the Documents for general introductions. API documents are available at our website.

Available Environments

We provide a complexity estimation for the games on several aspects. InfoSet Number: the number of information sets; Avg. InfoSet Size: the average number of states in a single information set; Action Size: the size of the action space. Name: the name that should be passed to env.make to create the game environment.

Game	InfoSet Number	Avg. InfoSet Size	Action Size	Name	Status
Blackjack (wiki, baike)	10^3	10^1	10^0	blackjack	Available
Leduc Hold’em (paper)	10^2	10^2	10^0	leduc-holdem	Available
Limit Texas Hold'em (wiki, baike)	10^14	10^3	10^0	limit-holdem	Available
Dou Dizhu (wiki, baike)	10^53 ~ 10^83	10^23	10^4	doudizhu	Available
Mahjong (wiki, baike)	10^121	10^48	10^2	mahjong	Available
No-limit Texas Hold'em (wiki, baike)	10^162	10^3	10^4	no-limit-holdem	Available
UNO (wiki, baike)	10^163	10^10	10^1	uno	Available
Sheng Ji (wiki, baike)	10^157 ~ 10^165	10^61	10^11	-	Developing

Evaluation

The perfomance is measured by winning rates through tournaments. Example outputs are as follows:

Cite this work

@article{zha2019rlcard,
  title={RLCard: A Toolkit for Reinforcement Learning in Card Games},
  author={Zha, Daochen and Lai, Kwei-Herng and Cao, Yuanpu and Huang, Songyi and Wei, Ruzhe and Guo, Junyu and Hu, Xia},
  journal={arXiv preprint arXiv:1910.04376},
  year={2019}
}

Contributing

Contribution to this project is greatly appreciated! Please create an issue for feedbacks/bugs. If you want to contribute codes, please refer to Contributing Guide.

Acknowledgements

We would like to thank JJ World Network Technology Co.,LTD for the generous support.

downseq/rlcard