Nash Equilibria in Games with Playerwise Concave Coupling Constraints: Existence and Computation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jordan, Philip, Kamgarpour, Maryam
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912883641679872
author Jordan, Philip
Kamgarpour, Maryam
author_facet Jordan, Philip
Kamgarpour, Maryam
contents We study the existence and computation of Nash equilibria in concave games where the players' admissible strategies are subject to shared coupling constraints. Under playerwise concavity of constraints, we prove existence of Nash equilibria. Our proof leverages topological fixed point theory and novel structural insights into the contractibility of feasible sets, and relaxes strong assumptions for existence in prior work. Having established existence, we address the question of whether in the presence of coupling constraints, playerwise independent learning dynamics have convergence guarantees. We address this positively for the class of potential games by designing a convergent algorithm. To account for the possibly nonconvex feasible region, we employ a log barrier regularized gradient ascent with adaptive stepsizes. Starting from an initial feasible strategy profile and under exact gradient feedback, the proposed method converges to an $ε$-approximate constrained Nash equilibrium within $\mathcal{O}(ε^{-3})$ iterations.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14032
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Nash Equilibria in Games with Playerwise Concave Coupling Constraints: Existence and Computation
Jordan, Philip
Kamgarpour, Maryam
Computer Science and Game Theory
Machine Learning
Multiagent Systems
We study the existence and computation of Nash equilibria in concave games where the players' admissible strategies are subject to shared coupling constraints. Under playerwise concavity of constraints, we prove existence of Nash equilibria. Our proof leverages topological fixed point theory and novel structural insights into the contractibility of feasible sets, and relaxes strong assumptions for existence in prior work. Having established existence, we address the question of whether in the presence of coupling constraints, playerwise independent learning dynamics have convergence guarantees. We address this positively for the class of potential games by designing a convergent algorithm. To account for the possibly nonconvex feasible region, we employ a log barrier regularized gradient ascent with adaptive stepsizes. Starting from an initial feasible strategy profile and under exact gradient feedback, the proposed method converges to an $ε$-approximate constrained Nash equilibrium within $\mathcal{O}(ε^{-3})$ iterations.
title Nash Equilibria in Games with Playerwise Concave Coupling Constraints: Existence and Computation
topic Computer Science and Game Theory
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2509.14032