English
Related papers

Related papers: A Policy Iteration Algorithm for N-player General-…

200 papers

We obtain global, non-asymptotic convergence guarantees for independent learning algorithms in competitive reinforcement learning settings with two agents (i.e., zero-sum stochastic games). We consider an episodic setting where in each…

Machine Learning · Computer Science 2021-01-13 Constantinos Daskalakis , Dylan J. Foster , Noah Golowich

We analyze a simple variant of the Goldfarb-Idnani (GI) dual active-set method for computing variational generalized Nash equilibria of strongly monotone N-player games with convex quadratic costs and shared affine inequality and equality…

Optimization and Control · Mathematics 2026-05-21 Alberto Bemporad

Learning in stochastic games is a notoriously difficult problem because, in addition to each other's strategic decisions, the players must also contend with the fact that the game itself evolves over time, possibly in a very complicated…

Computer Science and Game Theory · Computer Science 2022-10-18 Angeliki Giannou , Kyriakos Lotidis , Panayotis Mertikopoulos , Emmanouil-Vasileios Vlatakis-Gkaragkounis

Policy gradient algorithms are widely used in reinforcement learning and belong to the class of approximate dynamic programming methods. This paper studies two key policy gradient algorithms, the Natural Policy Gradient and the Gauss-Newton…

Systems and Control · Electrical Eng. & Systems 2026-05-11 Bowen Song , Sebastien Gros , Andrea Iannelli

Multi-agent games in dynamic nonlinear settings are challenging due to the time-varying interactions among the agents and the non-stationarity of the (potential) Nash equilibria. In this paper we consider model-free games, where agent…

Systems and Control · Electrical Eng. & Systems 2025-09-24 Eduardo Sebastián , Maitrayee Keskar , Eeman Iqbal , Eduardo Montijano , Carlos Sagüés , Nikolay Atanasov

Reinforcement learning has been successful both empirically and theoretically in single-agent settings, but extending these results to multi-agent reinforcement learning in general-sum Markov games remains challenging. This paper studies…

Machine Learning · Computer Science 2026-04-07 Narim Jeong , Donghwan Lee

Learning in a multi-agent system is challenging because agents are simultaneously learning and the environment is not stationary, undermining convergence guarantees. To address this challenge, this paper presents a new gradient-based…

Multiagent Systems · Computer Science 2019-03-08 Xinliang Song , Tonghan Wang , Chongjie Zhang

We study policy optimization algorithms for computing correlated equilibria in multi-player general-sum Markov Games. Previous results achieve $O(T^{-1/2})$ convergence rate to a correlated equilibrium and an accelerated $O(T^{-3/4})$…

Machine Learning · Computer Science 2024-05-03 Yang Cai , Haipeng Luo , Chen-Yu Wei , Weiqiang Zheng

Multi-agent interactions are increasingly important in the context of reinforcement learning, and the theoretical foundations of policy gradient methods have attracted surging research interest. We investigate the global convergence of…

Optimization and Control · Mathematics 2023-03-21 Sarath Pattathil , Kaiqing Zhang , Asuman Ozdaglar

We consider a finite horizon dynamic game with two players who observe their types privately and take actions, which are publicly observed. Players' types evolve as independent, controlled linear Gaussian processes and players incur…

Computer Science and Game Theory · Computer Science 2016-06-17 Deepanshu Vasal , Achilleas Anastasopoulos

We study infinite-horizon discounted two-player zero-sum Markov games, and develop a decentralized algorithm that provably converges to the set of Nash equilibria under self-play. Our algorithm is based on running an Optimistic Gradient…

Machine Learning · Computer Science 2021-07-08 Chen-Yu Wei , Chung-Wei Lee , Mengxiao Zhang , Haipeng Luo

We devise a policy-iteration algorithm for deterministic two-player discounted and mean-payoff games, that runs in polynomial time with high probability, on any input where each payoff is chosen independently from a sufficiently random…

Computer Science and Game Theory · Computer Science 2024-02-07 Bruno Loff , Mateusz Skomra

Recent results of Ye and Hansen, Miltersen and Zwick show that policy iteration for one or two player (perfect information) zero-sum stochastic games, restricted to instances with a fixed discount rate, is strongly polynomial. We show that…

Optimization and Control · Mathematics 2013-10-21 Marianne Akian , Stéphane Gaubert

This paper describes a new algorithm for decision making in two-player real-time video games. As with Monte Carlo Tree Search, the algorithm can be used without heuristics and has been developed for use in general video game AI. The…

Artificial Intelligence · Computer Science 2016-07-07 Jialin Liu , Diego Pérez-Liébana , Simon M. Lucas

Reinforcement learning is a powerful tool to learn the optimal policy of possibly multiple agents by interacting with the environment. As the number of agents grow to be very large, the system can be approximated by a mean-field problem.…

Optimization and Control · Mathematics 2020-08-18 Weichen Wang , Jiequn Han , Zhuoran Yang , Zhaoran Wang

This paper introduces Deep Policy Iteration (DPI), a novel approach that integrates the strengths of Neural Networks with the stability and convergence advantages of Policy Iteration (PI) to address high-dimensional stochastic Mean Field…

Optimization and Control · Mathematics 2024-07-15 Mouhcine Assouli , Badr Missaoui

Policy gradient methods are a powerful family of reinforcement learning algorithms for continuous control that optimize a policy directly. However, standard first-order methods often converge slowly. Second-order methods can accelerate…

Systems and Control · Electrical Eng. & Systems 2025-11-05 Amirreza Valaei , Arash Bahari Kordabad , Sadegh Soudjani

We examine global non-asymptotic convergence properties of policy gradient methods for multi-agent reinforcement learning (RL) problems in Markov potential games (MPG). To learn a Nash equilibrium of an MPG in which the size of state space…

Machine Learning · Computer Science 2022-08-08 Dongsheng Ding , Chen-Yu Wei , Kaiqing Zhang , Mihailo R. Jovanović

In this paper, we propose a second-order deterministic actor-critic framework in reinforcement learning that extends the classical deterministic policy gradient method to exploit curvature information of the performance function. Building…

Machine Learning · Computer Science 2025-11-13 Arash Bahari Kordabad , Dean Brandner , Sebastien Gros , Sergio Lucia , Sadegh Soudjani

Policy iteration enjoys a local quadratic rate of contraction, but its iterations are computationally expensive for Markov decision processes (MDPs) with a large number of states. In light of the connection between policy iteration and the…

Optimization and Control · Mathematics 2022-11-09 Matilde Gargiani , Dominic Liao-McPherson , Andrea Zanelli , John Lygeros