Successful Nash equilibrium agent for a three-player imperfect-information game

DOI10.3390/G9020033zbMATH Open1401.91018arXiv1804.04789OpenAlexW2797291350WikidataQ129710530 ScholiaQ129710530MaRDI QIDQ1651920FDOQ1651920

Authors: Sam Ganzfried, Austin Nowak, Joannier Pinales 

Publication date: 10 July 2018

Published in: Games (Search for Journal in Brave)

Abstract: Creating strong agents for games with more than two players is a major open problem in AI. Common approaches are based on approximating game-theoretic solution concepts such as Nash equilibrium, which have strong theoretical guarantees in two-player zero-sum games, but no guarantees in non-zero-sum games or in games with more than two players. We describe an agent that is able to defeat a variety of realistic opponents using an exact Nash equilibrium strategy in a 3-player imperfect-information game. This shows that, despite a lack of theoretical guarantees, agents based on Nash equilibrium strategies can be successful in multiplayer games after all.

Full work available at URL: https://arxiv.org/abs/1804.04789

Recommendations

• scientific article; zbMATH DE number 1329116
• Dynamics of three-agent games
• scientific article; zbMATH DE number 1998538
• scientific article; zbMATH DE number 2186530
• Publication:4504050
• Coalition-proof Nash equilibria and the core in three-player games
• scientific article; zbMATH DE number 1738583
• A three-person deterministic graphical game without Nash equilibria
• Approximate Nash Equilibria for Multi-player Games
• Perfect equilibria in games of incomplete information

zbMATH Keywords

game theoryartificial intelligenceNash equilibriumimperfect information

Mathematics Subject Classification ID

Noncooperative games (91A10) Agent technology and artificial intelligence (68T42) (n)-person games, (n>2) (91A06)

Cites Work

• Non-cooperative games
• Equilibrium Points of Bimatrix Games
• The complexity of two-person zero-sum games in extensive form
• Simple search methods for finding a Nash equilibrium
• A global Newton method to compute Nash equilibria.
• DeepStack: expert-level artificial intelligence in heads-up no-limit poker

Cited In (4)

• Three-player game-theoretic allocation of indivisible resources during natural disasters
• Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
• A survey of opponent modeling in adversarial domains
• Title not available (Why is that?)

Uses Software

• DeepStack

This page was built for publication: Successful Nash equilibrium agent for a three-player imperfect-information game

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1651920)