中文
相关论文

相关论文: Last-iterate Convergence of Decentralized Optimist…

200 篇论文

Zero-sum games arise in a wide variety of problems, including robust optimization and adversarial learning. However, algorithms deployed for finding a local Nash equilibrium in these games often converge to non-Nash stationary points. This…

计算机科学与博弈论 · 计算机科学 2025-09-30 Kushagra Gupta , Xinjie Liu , Ross Allen , Ufuk Topcu , David Fridovich-Keil

The Nash equilibrium is an important benchmark for behaviour in systems of strategic autonomous agents. Polymatrix games are a succinct and expressive representation of multiplayer games that model pairwise interactions between players. The…

计算机科学与博弈论 · 计算机科学 2016-03-17 Argyrios Deligkas , John Fearnley , Tobenna Peter Igwe , Rahul Savani

We propose locally convergent Nash equilibrium seeking algorithms for $N$-player noncooperative games, which use distributed event-triggered pseudo-gradient estimates. The proposed approach employs sinusoidal perturbations to estimate the…

最优化与控制 · 数学 2025-05-13 Victor Hugo Pereira Rodrigues , Tiago Roux Oliveira , Miroslav Krstic , Tamer Basar

Distributed Nash equilibrium (NE) seeking problem for multi-coalition games has attracted increasing attention in recent years, but the research mainly focuses on the case without agreement demand within coalitions. This paper considers a…

最优化与控制 · 数学 2021-12-10 Jialing Zhou , Yuezu Lv , Guanghui Wen , Jinhu Lv , Dezhi Zheng

We study the alternating gradient descent-ascent (AltGDA) algorithm in two-player zero-sum games. Alternating methods, where players take turns to update their strategies, have long been recognized as simple and practical approaches for…

计算机科学与博弈论 · 计算机科学 2026-03-03 Tianlong Nan , Shuvomoy Das Gupta , Garud Iyengar , Christian Kroer

We study the problem of learning a Nash equilibrium (NE) in Markov games which is a cornerstone in multi-agent reinforcement learning (MARL). In particular, we focus on infinite-horizon adversarial team Markov games (ATMGs) in which agents…

计算机科学与博弈论 · 计算机科学 2024-10-10 Fivos Kalogiannis , Jingming Yan , Ioannis Panageas

We consider a general-sum N-player linear-quadratic game with stochastic dynamics over a finite horizon and prove the global convergence of the natural policy gradient method to the Nash equilibrium. In order to prove the convergence of the…

最优化与控制 · 数学 2022-08-16 Ben Hambly , Renyuan Xu , Huining Yang

The distributed computation of a Nash equilibrium in aggregative games is gaining increased traction in recent years. Of particular interest is the mediator-free scenario where individual players only access or observe the decisions of…

计算机科学与博弈论 · 计算机科学 2023-06-26 Yongqiang Wang , Angelia Nedich

We explore the use of policy approximations to reduce the computational cost of learning Nash equilibria in zero-sum stochastic games. We propose a new Q-learning type algorithm that uses a sequence of entropy-regularized soft policies to…

机器学习 · 计算机科学 2021-06-29 Yue Guan , Qifan Zhang , Panagiotis Tsiotras

Multi-agent games are becoming an increasing prevalent formalism for the study of electronic commerce and auctions. The speed at which transactions can take place and the growing complexity of electronic marketplaces makes the study of…

计算机科学与博弈论 · 计算机科学 2013-01-18 Satinder Singh , Michael Kearns , Yishay Mansour

To optimally select a generalized Nash equilibrium, in this paper, we propose a semi-decentralized algorithm based on a double-layer Tikhonov regularization method. Technically, we extend the Tikhonov method for equilibrium selection in…

系统与控制 · 电气工程与系统科学 2023-04-26 Emilio Benenati , Wicak Ananduta , Sergio Grammatico

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…

机器学习 · 计算机科学 2026-05-19 Yevhen Shcherbinin , Arina Redina , Maxim Kalpin , Vlad Kochetov

There are only a few learning algorithms applicable to stochastic dynamic teams and games which generalize Markov decision processes to decentralized stochastic control problems involving possibly self-interested decision makers. Learning…

最优化与控制 · 数学 2016-05-03 Gürdal Arslan , Serdar Yüksel

Finding equilibria via gradient play in competitive multi-agent games has been attracting a growing amount of attention in recent years, with emphasis on designing efficient strategies where the agents operate in a decentralized and…

计算机科学与博弈论 · 计算机科学 2022-11-17 Ruicheng Ao , Shicong Cen , Yuejie Chi

We show by counterexample that policy-gradient algorithms have no guarantees of even local convergence to Nash equilibria in continuous action and state space multi-agent settings. To do so, we analyze gradient-play in N-player general-sum…

机器学习 · 计算机科学 2019-12-18 Eric Mazumdar , Lillian J. Ratliff , Michael I. Jordan , S. Shankar Sastry

We design the first fully-distributed algorithm for generalized Nash equilibrium seeking in aggregative games on a time-varying communication network, under partial-decision information, i.e., the agents have no direct access to the…

最优化与控制 · 数学 2022-06-16 Giuseppe Belgioioso , Angelia Nedić , Sergio Grammatico

We study discrete-time mean-field Markov games with infinite numbers of agents where each agent aims to minimize its ergodic cost. We consider the setting where the agents have identical linear state transitions and quadratic cost…

最优化与控制 · 数学 2019-10-17 Zuyue Fu , Zhuoran Yang , Yongxin Chen , Zhaoran Wang

In this paper, a multi-cluster game with high-order players is investigated. Different from the well-known multi-cluster games, the dynamics of players are taken into account in our problem. Due to the high-order dynamics of players,…

系统与控制 · 电气工程与系统科学 2021-06-28 Zhenhua Deng , Yangyang Liu

We derive the rate of convergence to Nash equilibria for the payoff-based algorithm proposed in \cite{tat_kam_TAC}. These rates are achieved under the standard assumption of convexity of the game, strong monotonicity and differentiability…

最优化与控制 · 数学 2022-02-24 Tatiana Tatarenko , Maryam Kamgarpour

While classic work in convex-concave min-max optimization relies on average-iterate convergence results, the emergence of nonconvex applications such as training Generative Adversarial Networks has led to renewed interest in last-iterate…

最优化与控制 · 数学 2019-10-29 Jacob Abernethy , Kevin A. Lai , Andre Wibisono