Saved in:
Bibliographic Details
Main Authors: Han, Minbiao, Zhang, Fengxue, Chen, Yuxin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.08318
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912118034399232
author Han, Minbiao
Zhang, Fengxue
Chen, Yuxin
author_facet Han, Minbiao
Zhang, Fengxue
Chen, Yuxin
contents This paper investigates the challenge of learning in black-box games, where the underlying utility function is unknown to any of the agents. While there is an extensive body of literature on the theoretical analysis of algorithms for computing the Nash equilibrium with complete information about the game, studies on Nash equilibrium in black-box games are less common. In this paper, we focus on learning the Nash equilibrium when the only available information about an agent's payoff comes in the form of empirical queries. We provide a no-regret learning algorithm that utilizes Gaussian processes to identify the equilibrium in such games. Our approach not only ensures a theoretical convergence rate but also demonstrates effectiveness across a variety collection of games through experimental validation.
format Preprint
id arxiv_https___arxiv_org_abs_2405_08318
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle No-Regret Learning of Nash Equilibrium for Black-Box Games via Gaussian Processes
Han, Minbiao
Zhang, Fengxue
Chen, Yuxin
Machine Learning
This paper investigates the challenge of learning in black-box games, where the underlying utility function is unknown to any of the agents. While there is an extensive body of literature on the theoretical analysis of algorithms for computing the Nash equilibrium with complete information about the game, studies on Nash equilibrium in black-box games are less common. In this paper, we focus on learning the Nash equilibrium when the only available information about an agent's payoff comes in the form of empirical queries. We provide a no-regret learning algorithm that utilizes Gaussian processes to identify the equilibrium in such games. Our approach not only ensures a theoretical convergence rate but also demonstrates effectiveness across a variety collection of games through experimental validation.
title No-Regret Learning of Nash Equilibrium for Black-Box Games via Gaussian Processes
topic Machine Learning
url https://arxiv.org/abs/2405.08318