PyTAG: Challenges and Opportunities for Reinforcement Learning in Tabletop Games

TL;DR

This paper introduces PyTAG, a Python API for reinforcement learning research in modern tabletop games, highlighting unique challenges and providing baseline results for RL agents in this domain.

Contribution

The paper presents PyTAG, a new API for RL in tabletop games, and offers initial training techniques and baseline results for RL agents in this setting.

Findings

Baseline RL agents trained with Proximal Policy Optimization

PyTAG enables RL research in 20+ modern tabletop games

Discussion of unique challenges in applying RL to tabletop games

Abstract

In recent years, Game AI research has made important breakthroughs using Reinforcement Learning (RL). Despite this, RL for modern tabletop games has gained little to no attention, even when they offer a range of unique challenges compared to video games. To bridge this gap, we introduce PyTAG, a Python API for interacting with the Tabletop Games framework (TAG). TAG contains a growing set of more than 20 modern tabletop games, with a common API for AI agents. We present techniques for training RL agents in these games and introduce baseline results after training Proximal Policy Optimisation algorithms on a subset of games. Finally, we discuss the unique challenges complex modern tabletop games provide, now open to RL research through PyTAG.