# Solving Zero-Sum Convex Markov Games

arXiv: https://arxiv.org/abs/2506.16120 · HTML: https://mlsanity.com/paper/2506.16120/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multi-agent reinforcement learning, one of 15 directions in Deep reinforcement learning methods.
- First posted on arXiv 19 Jun 2025.

## Placed in

- Deep reinforcement learning methods / [Multi-agent reinforcement learning](https://mlsanity.com/deeprl/multi-agent-reinforcement-learning/)

## Built on by (most cited first, 2 of 2)

- [Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria](https://mlsanity.com/paper/2602.12181/) (2026)
- [Online Learning on Hidden-Convex Losses via Algorithmic Equivalence: Optimal Regret, Geometric Barrier, and Bandit Feedback](https://mlsanity.com/paper/2605.26373/) (2026)

## Abstract (arXiv)

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.