English

Solving Zero-Sum Convex Markov Games

Computer Science and Game Theory 2025-06-23 v1 Machine Learning Multiagent Systems Optimization and Control

Abstract

We contribute the first provable guarantees of global convergence to Nash equilibria (NE) in two-player zero-sum convex Markov games (cMGs) by using independent policy gradient methods. Convex Markov games, recently defined by Gemp et al. (2024), extend Markov decision processes to multi-agent settings with preferences that are convex over occupancy measures, offering a broad framework for modeling generic strategic interactions. However, even the fundamental min-max case of cMGs presents significant challenges, including inherent nonconvexity, the absence of Bellman consistency, and the complexity of the infinite horizon. We follow a two-step approach. First, leveraging properties of hidden-convex--hidden-concave functions, we show that a simple nonconvex regularization transforms the min-max optimization problem into a nonconvex-proximal Polyak-Lojasiewicz (NC-pPL) objective. Crucially, this regularization can stabilize the iterates of independent policy gradient methods and ultimately lead them to converge to equilibria. Second, building on this reduction, we address the general constrained min-max problems under NC-pPL and two-sided pPL conditions, providing the first global convergence guarantees for stochastic nested and alternating gradient descent-ascent methods, which we believe may be of independent interest.

Keywords

Cite

@article{arxiv.2506.16120,
  title  = {Solving Zero-Sum Convex Markov Games},
  author = {Fivos Kalogiannis and Emmanouil-Vasileios Vlatakis-Gkaragkounis and Ian Gemp and Georgios Piliouras},
  journal= {arXiv preprint arXiv:2506.16120},
  year   = {2025}
}

Comments

To appear in the Proceedings of the 2025 International Conference on Machine Learning (ICML 2025)

R2 v1 2026-07-01T03:24:51.586Z