Transformer Guided Coevolution: Improved Team Selection in Multiagent Adversarial Team Games

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Rajbhandari, Pranav, Dasgupta, Prithviraj, Sofge, Donald
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917906374197248
author Rajbhandari, Pranav
Dasgupta, Prithviraj
Sofge, Donald
author_facet Rajbhandari, Pranav
Dasgupta, Prithviraj
Sofge, Donald
contents We consider the problem of team selection within multiagent adversarial team games. We propose BERTeam, a novel algorithm that uses a transformer-based deep neural network with Masked Language Model training to select the best team of players from a trained population. We integrate this with coevolutionary deep reinforcement learning, which trains a diverse set of individual players to choose from. We test our algorithm in the multiagent adversarial game Marine Capture-The-Flag, and find that BERTeam learns non-trivial team compositions that perform well against unseen opponents. For this game, we find that BERTeam outperforms MCAA, an algorithm that similarly optimizes team selection.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13769
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transformer Guided Coevolution: Improved Team Selection in Multiagent Adversarial Team Games
Rajbhandari, Pranav
Dasgupta, Prithviraj
Sofge, Donald
Artificial Intelligence
Multiagent Systems
Neural and Evolutionary Computing
We consider the problem of team selection within multiagent adversarial team games. We propose BERTeam, a novel algorithm that uses a transformer-based deep neural network with Masked Language Model training to select the best team of players from a trained population. We integrate this with coevolutionary deep reinforcement learning, which trains a diverse set of individual players to choose from. We test our algorithm in the multiagent adversarial game Marine Capture-The-Flag, and find that BERTeam learns non-trivial team compositions that perform well against unseen opponents. For this game, we find that BERTeam outperforms MCAA, an algorithm that similarly optimizes team selection.
title Transformer Guided Coevolution: Improved Team Selection in Multiagent Adversarial Team Games
topic Artificial Intelligence
Multiagent Systems
Neural and Evolutionary Computing
url https://arxiv.org/abs/2410.13769