dc.contributor.author | Balla, M | en_US |
dc.contributor.author | Long, GEM | en_US |
dc.contributor.author | Jeurissen, D | en_US |
dc.contributor.author | Goodman, J | en_US |
dc.contributor.author | Gaina, RD | en_US |
dc.contributor.author | Perez-Liebana, D | en_US |
dc.date.accessioned | 2024-02-19T15:50:21Z | |
dc.date.issued | 2023-01-01 | en_US |
dc.identifier.isbn | 9798350322774 | en_US |
dc.identifier.issn | 2325-4270 | en_US |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/94734 | |
dc.description.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. | en_US |
dc.rights | © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |
dc.title | PyTAG: Challenges and Opportunities for Reinforcement Learning in Tabletop Games | en_US |
dc.type | Conference Proceeding | |
dc.identifier.doi | 10.1109/CoG57401.2023.10333223 | en_US |
pubs.notes | Not known | en_US |
pubs.publication-status | Published | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |
qmul.funder | EPSRC Centre for Doctoral Training in Intelligent Games and Game Intelligence (IGGI)::epsrc | en_US |