# Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games

arXiv: https://arxiv.org/abs/2210.01050 · HTML: https://mlsanity.com/paper/2210.01050/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 60 references that are in the map.
- First posted on arXiv 3 Oct 2022.

## Builds on (most cited first, 30 of 31)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [A Theory of Regularized Markov Decision Processes](https://mlsanity.com/paper/1901.11275/) (2019)
- [On the Global Convergence Rates of Softmax Policy Gradient Methods](https://mlsanity.com/paper/2005.06392/) (2020)
- [Optimization, Learning, and Games with Predictable Sequences](https://mlsanity.com/paper/1311.1869/) (2013)
- [On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift](https://mlsanity.com/paper/1908.00261/) (2019)
- [Fast Global Convergence of Natural Policy Gradient Methods with Entropy Regularization](https://mlsanity.com/paper/2007.06558/) (2020)
- [Policy Mirror Descent for Reinforcement Learning: Linear Convergence, New Sampling Complexity, and Generalized Problem Classes](https://mlsanity.com/paper/2102.00135/) (2021)
- [Global Optimality Guarantees For Policy Gradient Methods](https://mlsanity.com/paper/1906.01786/) (2019)
- [On the Convergence Rates of Policy Gradient Methods](https://mlsanity.com/paper/2201.07443/) (2022)
- [V-Learning -- A Simple, Efficient, Decentralized Algorithm for Multiagent RL](https://mlsanity.com/paper/2110.14555/) (2021)
- [Provable Self-Play Algorithms for Competitive Reinforcement Learning](https://mlsanity.com/paper/2002.04017/) (2020)
- [Near-Optimal Reinforcement Learning with Self-Play](https://mlsanity.com/paper/2006.12007/) (2020)
- [A Sharp Analysis of Model-based Reinforcement Learning with Self-Play](https://mlsanity.com/paper/2010.01604/) (2020)
- [Independent Policy Gradient Methods for Competitive Reinforcement Learning](https://mlsanity.com/paper/2101.04233/) (2021)
- [Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium](https://mlsanity.com/paper/2002.07066/) (2020)
- [Last-Iterate Convergence: Zero-Sum Games and Constrained Min-Max Optimization](https://mlsanity.com/paper/1807.04252/) (2018)
- [Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity](https://mlsanity.com/paper/2007.07461/) (2020)
- [Policy Mirror Descent for Regularized Reinforcement Learning: A Generalized Framework with Linear Convergence](https://mlsanity.com/paper/2105.11066/) (2021)
- [Last-iterate Convergence of Decentralized Optimistic Gradient Descent/Ascent in Infinite-horizon Competitive Markov Games](https://mlsanity.com/paper/2102.04540/) (2021)
- [A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games](https://mlsanity.com/paper/2206.05825/) (2022)
- [Fast Policy Extragradient Methods for Competitive Games with Entropy Regularization](https://mlsanity.com/paper/2105.15186/) (2021)
- [Decentralized Q-Learning in Zero-sum Markov Games](https://mlsanity.com/paper/2106.02748/) (2021)
- [Softmax Policy Gradient Methods Can Take Exponential Time to Converge](https://mlsanity.com/paper/2102.11270/) (2021)
- [On the Linear convergence of Natural Policy Gradient Algorithm](https://mlsanity.com/paper/2105.01424/) (2021)
- [Exploration-Exploitation in Multi-Agent Competition: Convergence with Bounded Rationality](https://mlsanity.com/paper/2106.12928/) (2021)
- [Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games](https://mlsanity.com/paper/2102.08903/) (2021)
- [Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov Games](https://mlsanity.com/paper/2205.13746/) (2022)
- [Policy Optimization for Markov Games: Unified Framework and Faster Convergence](https://mlsanity.com/paper/2206.02640/) (2022)
- [O(T-1) Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games](https://mlsanity.com/paper/2209.12430/) (2022)

## Built on by (most cited first, 26 of 26)

- [Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback](https://mlsanity.com/paper/2303.02738/) (2023)
- [Breaking the Curse of Multiagents in a Large State Space: RL in Markov Games with Independent Linear Function Approximation](https://mlsanity.com/paper/2302.03673/) (2023)
- [Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback](https://mlsanity.com/paper/2503.08942/) (2025)
- [A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games](https://mlsanity.com/paper/2303.03100/) (2023)
- [Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games](https://mlsanity.com/paper/2310.09727/) (2023)
- [Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems](https://mlsanity.com/paper/2312.01127/) (2023)
- [Multi-Player Zero-Sum Markov Games with Networked Separable Interactions](https://mlsanity.com/paper/2307.09470/) (2023)
- [Adaptively Perturbed Mirror Descent for Learning in Games](https://mlsanity.com/paper/2305.16610/) (2023)
- [Asynchronous Gradient Play in Zero-Sum Multi-agent Games](https://mlsanity.com/paper/2211.08980/) (2022)
- [Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach](https://mlsanity.com/paper/2510.20235/) (2025)
- [Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2305.04819/) (2023)
- [Incentivize without Bonus: Provably Efficient Model-based Online Multi-agent RL for Markov Games](https://mlsanity.com/paper/2502.09780/) (2025)
- [Auto-exploration for online reinforcement learning](https://mlsanity.com/paper/2512.06244/) (2025)
- [Fast Computation of Optimal Transport via Entropy-Regularized Extragradient Methods](https://mlsanity.com/paper/2301.13006/) (2023)
- [Global Convergence of Policy Gradient Methods in Reinforcement Learning, Games and Control](https://mlsanity.com/paper/2310.05230/) (2023)
- [Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence Beyond the Minty Property](https://mlsanity.com/paper/2312.12067/) (2023)
- [Non-convex entropic mean-field optimization via Best Response flow](https://mlsanity.com/paper/2505.22760/) (2025)
- [Statistical and Algorithmic Foundations of Reinforcement Learning](https://mlsanity.com/paper/2507.14444/) (2025)
- [Differentiable Arbitrating in Zero-sum Markov Games](https://mlsanity.com/paper/2302.10058/) (2023)
- [Linear Convergence of Independent Natural Policy Gradient in Games with Entropy Regularization](https://mlsanity.com/paper/2405.02769/) (2024)
- [Configurable Mirror Descent: Towards a Unification of Decision Making](https://mlsanity.com/paper/2405.11746/) (2024)
- [TrafficGamer: Reliable and Flexible Traffic Simulation for Safety-Critical Scenarios with Game-Theoretic Oracles](https://mlsanity.com/paper/2408.15538/) (2024)
- [widetildeO(T-1) Convergence to (Coarse) Correlated Equilibria in Full-Information General-Sum Markov Games](https://mlsanity.com/paper/2403.07890/) (2024)
- [Last Iterate Convergence in Monotone Mean Field Games](https://mlsanity.com/paper/2410.05127/) (2024)
- [Fast Regularized Policy Mirror Descent with One-Step TD Updates](https://mlsanity.com/paper/2609.39837/) (2026)
- [Fast Last-Iterate Convergence in Zero-Sum Markov Games with Bandit Feedback](https://mlsanity.com/paper/2610.05968/) (2026)

## Abstract (arXiv)

Multi-Agent Reinforcement Learning (MARL) -- where multiple agents learn to interact in a shared dynamic environment -- permeates across a wide range of critical applications. While there has been substantial progress on understanding the global convergence of policy optimization methods in single-agent RL, designing and analysis of efficient policy optimization algorithms in the MARL setting present significant challenges, which unfortunately, remain highly inadequately addressed by existing theory. In this paper, we focus on the most basic setting of competitive multi-agent RL, namely two-player zero-sum Markov games, and study equilibrium finding algorithms in both the infinite-horizon discounted setting and the finite-horizon episodic setting. We propose a single-loop policy optimization method with symmetric updates from both agents, where the policy is updated via the entropy-regularized optimistic multiplicative weights update (OMWU) method and the value is updated on a slower timescale. We show that, in the full-information tabular setting, the proposed method achieves a finite-time last-iterate linear convergence to the quantal response equilibrium of the regularized problem, which translates to a sublinear last-iterate convergence to the Nash equilibrium by controlling the amount of regularization. Our convergence results improve upon the best known iteration complexities, and lead to a better understanding of policy optimization in competitive Markov games.