AISTATS 2024poster6 citations

Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games

Yang Cai, Haipeng Luo, Chen-Yu Wei, Weiqiang Zheng

Abstract

We study policy optimization algorithms for computing correlated equilibria in multi-player general-sum Markov Games. Previous results achieve $\tilde{O}(T^{-1/2})$ convergence rate to a correlated equilibrium and an accelerated $\tilde{O}(T^{-3/4})$ convergence rate to the weaker notion of coarse correlated equilibrium. In this paper, we improve both results significantly by providing an uncoupled policy optimization algorithm that attains a near-optimal $\tilde{O}(T^{-1})$ convergence rate for computing a correlated equilibrium. Our algorithm is constructed by combining two main elements (i) smooth value updates and (ii) the \emph{optimistic-follow-the-regularized-leader} algorithm with the log barrier regularizer.

BibTeX
@InProceedings{pmlr-v238-cai24a,
  title = 	 {Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum {M}arkov Games},
  author =       {Cai, Yang and Luo, Haipeng and Wei, Chen-Yu and Zheng, Weiqiang},
  booktitle = 	 {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {3889--3897},
  year = 	 {2024},
  editor = 	 {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen},
  volume = 	 {238},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {02--04 May},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v238/cai24a/cai24a.pdf},
  url = 	 {https://proceedings.mlr.press/v238/cai24a.html},
  abstract = 	 {We study policy optimization algorithms for computing correlated equilibria in multi-player general-sum Markov Games. Previous results achieve $\tilde{O}(T^{-1/2})$ convergence rate to a correlated equilibrium and an accelerated $\tilde{O}(T^{-3/4})$ convergence rate to the weaker notion of coarse correlated equilibrium. In this paper, we improve both results significantly by providing an uncoupled policy optimization algorithm that attains a near-optimal $\tilde{O}(T^{-1})$ convergence rate for computing a correlated equilibrium. Our algorithm is constructed by combining two main elements (i) smooth value updates and (ii) the \emph{optimistic-follow-the-regularized-leader} algorithm with the log barrier regularizer.}
}
Near-Optimal Policy Optimization for Correlated Equilibrium in General-Sum Markov Games · AISTATS 2024