Opponent Modeling in Multiplayer Imperfect-Information Games

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ganzfried, Sam, Wang, Kevin A., Chiswick, Max
Natura: Preprint
Pubblicazione: 2022
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913449345286144
author Ganzfried, Sam
Wang, Kevin A.
Chiswick, Max
author_facet Ganzfried, Sam
Wang, Kevin A.
Chiswick, Max
contents In many real-world settings agents engage in strategic interactions with multiple opposing agents who can employ a wide variety of strategies. The standard approach for designing agents for such settings is to compute or approximate a relevant game-theoretic solution concept such as Nash equilibrium and then follow the prescribed strategy. However, such a strategy ignores any observations of opponents' play, which may indicate shortcomings that can be exploited. We present an approach for opponent modeling in multiplayer imperfect-information games where we collect observations of opponents' play through repeated interactions. We run experiments against a wide variety of real opponents and exact Nash equilibrium strategies in three-player Kuhn poker and show that our algorithm significantly outperforms all of the agents, including the exact Nash equilibrium strategies.
format Preprint
id arxiv_https___arxiv_org_abs_2212_06027
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Opponent Modeling in Multiplayer Imperfect-Information Games
Ganzfried, Sam
Wang, Kevin A.
Chiswick, Max
Computer Science and Game Theory
Artificial Intelligence
Multiagent Systems
Theoretical Economics
In many real-world settings agents engage in strategic interactions with multiple opposing agents who can employ a wide variety of strategies. The standard approach for designing agents for such settings is to compute or approximate a relevant game-theoretic solution concept such as Nash equilibrium and then follow the prescribed strategy. However, such a strategy ignores any observations of opponents' play, which may indicate shortcomings that can be exploited. We present an approach for opponent modeling in multiplayer imperfect-information games where we collect observations of opponents' play through repeated interactions. We run experiments against a wide variety of real opponents and exact Nash equilibrium strategies in three-player Kuhn poker and show that our algorithm significantly outperforms all of the agents, including the exact Nash equilibrium strategies.
title Opponent Modeling in Multiplayer Imperfect-Information Games
topic Computer Science and Game Theory
Artificial Intelligence
Multiagent Systems
Theoretical Economics
url https://arxiv.org/abs/2212.06027