Policy updates show fast stable solutions in multiplayer networked games

Last-Iterate Convergence of Policy Dynamics in Zero-Sum Networked Separable Markov Games

Computer Science and Game Theory

Summary

Finding stable strategies, called Nash equilibria, in games with many players is usually very hard. Games where two players compete zero-sum have faster ways to find these strategies, but more complex multiplayer games have been tricky to solve efficiently. The authors study a special type of multiplayer game where many players interact in pairs and propose a new method for updating their strategies. Their method quickly converges to a stable solution, and importantly, this stability appears at the last step they compute, making it practical and reliable. This work extends known fast techniques from simple two-player games to more complex multiplayer scenarios.

Nash equilibriumMarkov gameszero-sumpolicy optimizationlast-iterate convergencemultiplicative weights updateentropy regularizationmulti-player gamesdynamic programminggame theory

Authors

Zailin Ma

Abstract

Solving Nash equilibria for general multi-player Markov games is computationally intractable, while two-player zero-sum Markov games admit fast last-iterate policy-optimization methods. Finite-horizon zero-sum networked separable Markov games occupy an important middle ground: they retain global competition structure through pairwise interactions, while preserving computational tractability of Nash equilibria (NE) in the full-information and known-transition setting. Existing algorithms for this class either proceed through equilibrium-collapse arguments for a simplified setting where a single controller determines the transition probability, or backward dynamic programming that relies on equilibrium solvers at each stage. However, the design and analysis of direct policy-update approaches remain inadequate. To address this issue, we propose the entropy-regularized optimistic multiplicative weights update (ER-OMWU), a complementary single-loop policy dynamic that updates players' policies symmetrically and returns an approximate NE in the last iteration. We provide a first last-iterate convergence analysis of policy dynamics in the games of interest: after $\widetilde{O}(1/ε)$ iterations, the returned policy is an $ε$-approximate Nash equilibrium. The result preserves the near-linear convergence rate achieved by policy optimization in two-player zero-sum Markov games, but extends the policy-dynamics viewpoint to a more complicated but structured multi-player setting.