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

arXiv:2404.00045v1 Announce Type: cross
Abstract: In this paper, we investigate the impact of introducing relative entropy regularization on the Nash Equilibria (NE) of General-Sum $N$-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 …

abstract agent arxiv cs.ai cs.gt cs.lg cs.ma entropy equilibria equilibrium games general impact linear nash equilibrium optimization paper policies policy regularization type