RainbowArena: A Multi-Agent Toolkit for Reinforcement Learning and Large Language Models in Competitive Tabletop Games

Yingzhuo Liu (Beijing University of Posts and Telecommunications), Shuodi Liu (Beijing University of Posts and Telecommunications), Hongsong Tang (Beijing University of Posts and Telecommunications), Yubing Ma (Beijing University of Posts and Telecommunications), Zikang Li (Beijing University of Posts and Telecommunications), Junge Zhang (Institute of Automation, Chinese Academy of Science), Liuyu Xiang (Beijing University of Posts and Telecommunications), Zhaofeng He (Beijing University of Post and Telecommunication)

Abstract

Tabletop games have gained little to no attention, despite offering a range of unique challenges compared to card or board games. We introduce RainbowArena, an open-source toolkit for reinforcement learning and large language models in competitive tabletop games. The goal of RainbowArena is to provide a unified, scalable platform that supports both Reinforcement Learning (RL) and Large Language Models (LLM), and push forward the research in tabletop games. RainbowArena consists of three modules: game, agent and evaluation. We design unified components and interfaces for various tabletop games. To better integrate with game environments, we devise an efficient self-play framework for RL agents, and a standardized prompt structure for LLM agents. Additionally, agents of all types can be evaluated within the evaluation framework. Finally, we evaluate various types of agents across different games and analyze the runtime efficiency for each game.