PyTAG: Tabletop Games for Multi-Agent Reinforcement Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Balla, Martin, Long, George E. M., Goodman, James, Gaina, Raluca D., Perez-Liebana, Diego
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914814782078976
author Balla, Martin
Long, George E. M.
Goodman, James
Gaina, Raluca D.
Perez-Liebana, Diego
author_facet Balla, Martin
Long, George E. M.
Goodman, James
Gaina, Raluca D.
Perez-Liebana, Diego
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18123
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PyTAG: Tabletop Games for Multi-Agent Reinforcement Learning
Balla, Martin
Long, George E. M.
Goodman, James
Gaina, Raluca D.
Perez-Liebana, Diego
Artificial Intelligence
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.
title PyTAG: Tabletop Games for Multi-Agent Reinforcement Learning
topic Artificial Intelligence
url https://arxiv.org/abs/2405.18123