RLCard: A Toolkit for Reinforcement Learning in Card Games

TL;DR

RLCard is an open-source toolkit designed to facilitate reinforcement learning research in various card games, supporting multiple environments and aiming to advance AI in imperfect information multi-agent domains.

Contribution

It introduces a comprehensive, easy-to-use toolkit for reinforcement learning in card games, enabling research in complex, multi-agent, imperfect information environments.

Findings

Supports diverse card game environments including Blackjack and Mahjong.

Provides comprehensive evaluations of the environments.

Facilitates research in large state and action spaces with sparse rewards.

Abstract

RLCard is an open-source toolkit for reinforcement learning research in card games. It supports various card environments with easy-to-use interfaces, including Blackjack, Leduc Hold'em, Texas Hold'em, UNO, Dou Dizhu and Mahjong. 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. In this paper, we provide an overview of the key components in RLCard, a discussion of the design principles, a brief introduction of the interfaces, and comprehensive evaluations of the environments. The codes and documents are available at https://github.com/datamllab/rlcard