English
Related papers

Related papers: Fast Convergence of Optimistic Gradient Ascent in …

200 papers

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

A recent emerging trend in the literature on learning in games has been concerned with providing faster learning dynamics for correlated and coarse correlated equilibria in normal-form games. Much less is known about the significantly more…

Computer Science and Game Theory · Computer Science 2022-02-14 Ioannis Anagnostides , Gabriele Farina , Christian Kroer , Andrea Celli , Tuomas Sandholm

The approximation of mixed Nash equilibria (MNE) for zero-sum games with mean-field interacting players has recently raised much interest in machine learning. In this paper we propose a mean-field gradient descent dynamics for finding the…

Optimization and Control · Mathematics 2025-05-13 Yulong Lu , Pierre Monmarché

The congestion game is a powerful model that encompasses a range of engineering systems such as traffic networks and resource allocation. It describes the behavior of a group of agents who share a common set of $F$ facilities and take…

Computer Science and Game Theory · Computer Science 2023-06-27 Jing Dong , Jingyu Wu , Siwei Wang , Baoxiang Wang , Wei Chen

We study model-based and model-free policy optimization in a class of nonzero-sum stochastic dynamic games called linear quadratic (LQ) deep structured games. In such games, players interact with each other through a set of weighted…

Computer Science and Game Theory · Computer Science 2020-12-15 Masoud Roudneshin , Jalal Arabneydi , Amir G. Aghdam

Fictitious play (FP) is a well-studied algorithm that enables agents to learn Nash equilibrium in games with certain reward structures. However, when agents have no prior knowledge of the reward functions, FP faces a major challenge: the…

Computer Science and Game Theory · Computer Science 2025-08-28 Semih Kara , Tamer Başar

Action-graph games (AGGs) are a fully expressive game representation which can compactly express both strict and context-specific independence between players' utility functions. Actions are represented as nodes in a graph G, and the payoff…

Computer Science and Game Theory · Computer Science 2012-07-19 Navin Bhat , Kevin Leyton-Brown

Stochastic min-max optimization has gained interest in the machine learning community with the advancements in GANs and adversarial training. Although game optimization is fairly well understood in the deterministic setting, some issues…

Machine Learning · Computer Science 2024-03-27 Juan Ramirez , Rohan Sukumaran , Quentin Bertrand , Gauthier Gidel

In this paper, we provide exponential rates of convergence to the interior Nash equilibrium for continuous-time dual-space game dynamics such as mirror descent (MD) and actor-critic (AC). We perform our analysis in $N$-player continuous…

Optimization and Control · Mathematics 2022-02-04 Bolin Gao , Lacra Pavel

Learning in zero-sum games studies a situation where multiple agents competitively learn their strategy. In such multi-agent learning, we often see that the strategies cycle around their optimum, i.e., Nash equilibrium. When a game…

Computer Science and Game Theory · Computer Science 2025-03-06 Yuma Fujimoto , Kaito Ariu , Kenshi Abe

In large systems, it is important for agents to learn to act effectively, but sophisticated multi-agent learning algorithms generally do not scale. An alternative approach is to find restricted classes of games where simple, efficient…

Multiagent Systems · Computer Science 2009-03-16 Ian A. Kash , Eric J. Friedman , Joseph Y. Halpern

We study online reinforcement learning in average-reward stochastic games (SGs). An SG models a two-player zero-sum game in a Markov environment, where state transitions and one-step payoffs are determined simultaneously by a learner and an…

Machine Learning · Computer Science 2017-12-05 Chen-Yu Wei , Yi-Te Hong , Chi-Jen Lu

The remarkable success of the Adam in training neural networks has naturally led to the widespread use of its descent-ascent counterpart, Adam-DA, for solving zero-sum games. Despite its popularity in practice, a rigorous theoretical…

Machine Learning · Computer Science 2026-05-20 Yi Feng , Weiming Ou , Xiao Wang

Zero-sum games are a fundamental setting for adversarial training and decision-making in multi-agent learning (MAL). Existing methods often ensure convergence to (approximate) Nash equilibria by introducing a form of regularization. Yet,…

Multiagent Systems · Computer Science 2026-02-10 Tuo Zhang , Leonardo Stella

Bargaining games, where agents attempt to agree on how to split utility, are an important class of games used to study economic behavior, which motivates a study of online learning algorithms in these games. In this work, we tackle when…

Computer Science and Game Theory · Computer Science 2025-07-08 Serafina Kamp , Reese Liebman , Benjamin Fish

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

Decoding how rational agents should behave in shared systems remains a critical challenge within theoretical computer science, artificial intelligence and economics studies. Central to this challenge is the task of computing the solution…

Computer Science and Game Theory · Computer Science 2025-01-07 Dongge Wang , Xiang Yan , Zehao Dou , Wenhan Huang , Yaodong Yang , Xiaotie Deng

The predominant paradigm in evolutionary game theory and more generally online learning in games is based on a clear distinction between a population of dynamic agents that interact given a fixed, static game. In this paper, we move away…

Computer Science and Game Theory · Computer Science 2020-12-16 Stratis Skoulakis , Tanner Fiez , Ryann Sim , Georgios Piliouras , Lillian Ratliff

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

An ideal strategy in zero-sum games should not only grant the player an average reward no less than the value of Nash equilibrium, but also exploit the (adaptive) opponents when they are suboptimal. While most existing works in Markov games…

Machine Learning · Computer Science 2022-06-15 Qinghua Liu , Yuanhao Wang , Chi Jin