Successful Nash Equilibrium Agent for a 3-Player Imperfect-Information Game

TL;DR

This paper presents an agent that successfully uses an exact Nash equilibrium strategy to defeat various opponents in a 3-player imperfect-information game, demonstrating practical effectiveness despite limited theoretical guarantees.

Contribution

It introduces a novel agent employing exact Nash equilibrium strategies for multiplayer imperfect-information games, showing practical success where theoretical guarantees are lacking.

Findings

Agent defeats diverse realistic opponents.

Nash equilibrium strategies are effective in multiplayer settings.

Challenges of theoretical guarantees in non-zero-sum multiplayer games are addressed.

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.