Saved in:
Bibliographic Details
Main Authors: Shukla, Apurv, Subramanian, Vijay, Zhao, Andy, Jain, Rahul
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.09928
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911054041186304
author Shukla, Apurv
Subramanian, Vijay
Zhao, Andy
Jain, Rahul
author_facet Shukla, Apurv
Subramanian, Vijay
Zhao, Andy
Jain, Rahul
contents We introduce a new solution concept for bounded rational agents in finite normal-form general-sum games called Generalized Quantal Response Equilibrium (GQRE) which generalizes Quantal Response Equilibrium~\citep{mckelvey1995quantal}. In our setup, each player maximizes a smooth, regularized expected utility of the mixed profiles used, reflecting bounded rationality that subsumes stochastic choice. After establishing existence under mild conditions, we present computationally efficient no-regret independent learning via smoothened versions of the Frank-Wolfe algorithm. Our algorithm uses noisy but correlated gradient estimates generated via a simulation oracle that reports on repeated plays of the game. We analyze convergence properties of our algorithm under assumptions that ensure uniqueness of equilibrium, using a class of gap functions that generalize the Nash gap. We end by demonstrating the effectiveness of our method on a set of complex general-sum games such as high-rank two-player games, large action two-player games, and known examples of difficult multi-player games.
format Preprint
id arxiv_https___arxiv_org_abs_2507_09928
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generalized Quantal Response Equilibrium: Existence and Efficient Learning
Shukla, Apurv
Subramanian, Vijay
Zhao, Andy
Jain, Rahul
Computer Science and Game Theory
Optimization and Control
We introduce a new solution concept for bounded rational agents in finite normal-form general-sum games called Generalized Quantal Response Equilibrium (GQRE) which generalizes Quantal Response Equilibrium~\citep{mckelvey1995quantal}. In our setup, each player maximizes a smooth, regularized expected utility of the mixed profiles used, reflecting bounded rationality that subsumes stochastic choice. After establishing existence under mild conditions, we present computationally efficient no-regret independent learning via smoothened versions of the Frank-Wolfe algorithm. Our algorithm uses noisy but correlated gradient estimates generated via a simulation oracle that reports on repeated plays of the game. We analyze convergence properties of our algorithm under assumptions that ensure uniqueness of equilibrium, using a class of gap functions that generalize the Nash gap. We end by demonstrating the effectiveness of our method on a set of complex general-sum games such as high-rank two-player games, large action two-player games, and known examples of difficult multi-player games.
title Generalized Quantal Response Equilibrium: Existence and Efficient Learning
topic Computer Science and Game Theory
Optimization and Control
url https://arxiv.org/abs/2507.09928