PyTAG: Tabletop Games for Multi-Agent Reinforcement Learning

TL;DR

PyTAG is a new framework for multi-agent reinforcement learning in tabletop games, enabling research on complex game environments and training RL agents through self-play and evaluation against various strategies.

Contribution

Introduction of PyTAG, a versatile framework supporting multiple tabletop games for multi-agent RL research and demonstrating training of RL agents via self-play.

Findings

RL agents trained with PyTAG show competitive performance

Self-play effectively trains agents in complex tabletop environments

Framework facilitates future research in multi-agent RL

Abstract

Modern Tabletop Games present various interesting challenges for Multi-agent Reinforcement Learning. In this paper, 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. Additionally, we highlight the technical challenges that involve training Reinforcement Learning agents on these games. To explore the Multi-agent setting provided by PyTAG we train the popular Proximal Policy Optimisation 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.