Litcius/Paper detail

RLCard: A Platform for Reinforcement Learning in Card Games

Daochen Zha, Kwei-Herng Lai, Songyi Huang, Yuanpu Cao, K. Rajesh Reddy, Juan Carlos Vargas, Alex Hoang Hai Nguyen, Ruzhe Wei, Junyu Guo, Xia Hu

202032 citationsDOIOpen Access PDF

Abstract

We present RLCard, a Python platform for reinforcement learning research and development in card games. RLCard supports various card environments and several baseline algorithms with unified easy-to-use interfaces, aiming at bridging reinforcement learning and imperfect information games. The platform provides flexible configurations of state representation, action encoding, and reward design. RLCard also supports visualizations for algorithm debugging. In this demo, we showcase two representative environments and their visualization results. We conclude this demo with challenges and research opportunities brought by RLCard. A video is available on YouTube.

Topics & Concepts

Computer scienceReinforcement learningDebuggingPython (programming language)Human–computer interactionVisualizationBridging (networking)MultimediaArtificial intelligenceProgramming languageComputer networkArtificial Intelligence in GamesReinforcement Learning in RoboticsSports Analytics and Performance