English
Related papers

Related papers: Policy-Gradient Algorithms Have No Guarantees of C…

200 papers

Learning processes in games explain how players grapple with one another in seeking an equilibrium. We study a natural model of learning based on individual gradients in two-player continuous games. In such games, the arguably natural…

Computer Science and Game Theory · Computer Science 2020-11-10 Benjamin J. Chasnov , Daniel Calderone , Behçet Açıkmeşe , Samuel A. Burden , Lillian J. Ratliff

Zero-sum stochastic games are easy to solve as they can be cast as simple Markov decision processes. This is however not the case with general-sum stochastic games. A fairly general optimization problem formulation is available for…

Machine Learning · Computer Science 2015-07-02 H. L. Prasad , Shalabh Bhatnagar

This work focuses on the entropy-regularized independent natural policy gradient (NPG) algorithm in multi-agent reinforcement learning. In this work, agents are assumed to have access to an oracle with exact policy evaluation and seek to…

Machine Learning · Computer Science 2024-05-07 Youbang Sun , Tao Liu , P. R. Kumar , Shahin Shahrampour

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

Constrained Markov games offer a formal mathematical framework for modeling multi-agent reinforcement learning problems where the behavior of the agents is subject to constraints. In this work, we focus on the recently introduced class of…

Machine Learning · Computer Science 2024-02-29 Philip Jordan , Anas Barakat , Niao He

We present a policy iteration algorithm for the infinite-horizon N-player general-sum deterministic linear quadratic dynamic games and compare it to policy gradient methods. We demonstrate that the proposed policy iteration algorithm is…

Optimization and Control · Mathematics 2024-10-07 Yuxiang Guan , Giulio Salizzoni , Maryam Kamgarpour , Tyler H. Summers

We study Markov potential games under the infinite horizon average reward criterion. Most previous studies have been for discounted rewards. We prove that both algorithms based on independent policy gradient and independent natural policy…

Machine Learning · Computer Science 2024-03-12 Min Cheng , Ruida Zhou , P. R. Kumar , Chao Tian

In this paper, we study finite-agent linear-quadratic games on graphs. Specifically, we propose a comprehensive framework that extends the existing literature by incorporating heterogeneous and interpretable player interactions. Compared to…

Optimization and Control · Mathematics 2025-11-19 Ruimeng Hu , Jihao Long , Haosheng Zhou

We consider the problem of finding a Nash equilibrium (NE) in a general-sum game, where player $i$'s objective is $f_i(x)=f_i(x_1,...,x_n)$, with $x_j\in\mathbb{R}^{d_j}$ denoting the strategy variables of player $j$. Our focus is on…

Computer Science and Game Theory · Computer Science 2026-02-13 Yutong Chao , Jalal Etesami

Towards characterizing the optimization landscape of games, this paper analyzes the stability of gradient-based dynamics near fixed points of two-player continuous games. We introduce the quadratic numerical range as a method to…

Computer Science and Game Theory · Computer Science 2021-01-15 Benjamin J. Chasnov , Daniel Calderone , Behçet Açıkmeşe , Samuel A. Burden , Lillian J. Ratliff

Multi-agent policy-gradient methods have been shown to converge locally near stable Nash equilibria. Local convergence, however, does not determine which equilibrium is reached. We study this question through basin-entry probability with…

Machine Learning · Computer Science 2026-05-19 Yevhen Shcherbinin , Arina Redina , Maxim Kalpin , Vlad Kochetov

We introduce a generalization of zero-sum network multiagent matrix games and prove that alternating gradient descent converges to the set of Nash equilibria at rate $O(1/T)$ for this set of games. Alternating gradient descent obtains this…

Computer Science and Game Theory · Computer Science 2021-10-07 James P. Bailey

Finding Nash equilibria in two-player zero-sum imperfect-information games remains a central challenge in multi-agent reinforcement learning. Recent multi-round regularization methods offer a promising direction, yet existing approaches…

Machine Learning · Computer Science 2026-05-01 Eason Yu , Tzu Hao Liu , Clément L. Canonne , Yunke Wang , Chang Xu , Nguyen H. Tran , Stefano V. Albrecht

We study the problem of computing an approximate Nash equilibrium of continuous-action game without access to gradients. Such game access is common in reinforcement learning settings, where the environment is typically treated as a black…

Computer Science and Game Theory · Computer Science 2023-08-30 Carlos Martin , Tuomas Sandholm

Multi-agent learning algorithms have been shown to display complex, unstable behaviours in a wide array of games. In fact, previous works indicate that convergent behaviours are less likely to occur as the total number of agents increases.…

Computer Science and Game Theory · Computer Science 2024-03-26 Aamal Hussain , Dan Leonte , Francesco Belardinelli , Georgios Piliouras

Recent advances at the intersection of dense large graph limits and mean field games have begun to enable the scalable analysis of a broad class of dynamical sequential games with large numbers of agents. So far, results have been largely…

Computer Science and Game Theory · Computer Science 2022-02-21 Kai Cui , Heinz Koeppl

The framework of multi-agent learning explores the dynamics of how individual agent strategies evolve in response to the evolving strategies of other agents. Of particular interest is whether or not agent strategies converge to well known…

Computer Science and Game Theory · Computer Science 2023-11-21 Sarah A. Toonsi , Jeff S. Shamma

There has been significant recent progress in algorithms for approximation of Nash equilibrium in large two-player zero-sum imperfect-information games and exact computation of Nash equilibrium in multiplayer strategic-form games. While…

Computer Science and Game Theory · Computer Science 2025-10-01 Sam Ganzfried

Behavioral diversity, expert imitation, fairness, safety goals and others give rise to preferences in sequential decision making domains that do not decompose additively across time. We introduce the class of convex Markov games that allow…

Computer Science and Game Theory · Computer Science 2025-06-17 Ian Gemp , Andreas Haupt , Luke Marris , Siqi Liu , Georgios Piliouras

Finding Nash equilibria in two-player zero-sum continuous games is a central problem in machine learning, e.g. for training both GANs and robust models. The existence of pure Nash equilibria requires strong conditions which are not…

Machine Learning · Computer Science 2021-05-07 Carles Domingo-Enrich , Samy Jelassi , Arthur Mensch , Grant Rotskoff , Joan Bruna