PyTAG: Tabletop Games for Multi-Agent Reinforcement Learning

Modern Tabletop Games present various interesting challenges for multiagent reinforcement learning. In this article, we introduce PyTAG, a new framework that supports interacting with a large collection of games implemented in the Tabletop Games framework. In this work, we highlight the challenges tabletop games provide, from a game-playing agent perspective, along with the opportunities they provide for future research. In addition, we highlight the technical challenges that involve training reinforcement learning agents on these games. To explore the multiagent setting provided by PyTAG, we train the popular proximal policy optimization reinforcement learning algorithm using self-play on a subset of games and evaluate the trained policies against some simple agents and Monte Carlo tree search implemented in the Tabletop Games framework.