English

Policy Optimization finds Nash Equilibrium in Regularized General-Sum LQ Games

Computer Science and Game Theory 2024-09-16 v2 Artificial Intelligence Machine Learning Multiagent Systems

Abstract

In this paper, we investigate the impact of introducing relative entropy regularization on the Nash Equilibria (NE) of General-Sum NN-agent games, revealing the fact that the NE of such games conform to linear Gaussian policies. Moreover, it delineates sufficient conditions, contingent upon the adequacy of entropy regularization, for the uniqueness of the NE within the game. As Policy Optimization serves as a foundational approach for Reinforcement Learning (RL) techniques aimed at finding the NE, in this work we prove the linear convergence of a policy optimization algorithm which (subject to the adequacy of entropy regularization) is capable of provably attaining the NE. Furthermore, in scenarios where the entropy regularization proves insufficient, we present a δ\delta-augmentation technique, which facilitates the achievement of an ϵ\epsilon-NE within the game.

Keywords

Cite

@article{arxiv.2404.00045,
  title  = {Policy Optimization finds Nash Equilibrium in Regularized General-Sum LQ Games},
  author = {Muhammad Aneeq uz Zaman and Shubham Aggarwal and Melih Bastopcu and Tamer Başar},
  journal= {arXiv preprint arXiv:2404.00045},
  year   = {2024}
}

Comments

Accepted for Conference on Decision and Control 2024

R2 v1 2026-06-28T15:38:38.343Z