Multiagent Online Learning in Time-Varying Games

被引：5

作者：

Duvocelle, Benoit ^{[1
]}

Mertikopoulos, Panayotis ^{[2
,3
]}

Staudigl, Mathias ^{[4
]}

Vermeulen, Dries ^{[1
]}

机构：

[1] Maastricht Univ, Dept Quantitat Econ, NL-6200 MD Maastricht, Netherlands

[2] Univ Grenoble Alpes, LIG, Grenoble INP, CNRS,Inria, F-38000 Grenoble, France

[3] Criteo AI Lab, F-38130 Echirolles, France

[4] Maastricht Univ, Dept Adv Comp Sci, NL-6200 MD Maastricht, Netherlands

来源：

MATHEMATICS OF OPERATIONS RESEARCH | 2023年 / 48卷 / 02期

关键词：

dynamic regret; Nash equilibrium; mirror descent; time-varying games; STOCHASTIC-APPROXIMATION; OPTIMIZATION; DYNAMICS; CONVERGENCE; GRADIENT; DESCENT; PLAY; FORM;

D O I：

10.1287/moor.2022.1283

中图分类号：

C93 [管理学]; O22 [运筹学];

学科分类号：

070105 ; 12 ; 1201 ; 1202 ; 120202 ;

摘要：

We examine the long-run behavior of multiagent online learning in games that evolve over time. Specifically, we focus on a wide class of policies based on mirror descent, and we show that the induced sequence of play (a) converges to a Nash equilibrium in time-varying games that stabilize in the long run to a strictly monotone limit, and (b) it stays asymptotically close to the evolving equilibrium of the sequence of stage games (assuming they are strongly monotone). Our results apply to both gradient- and payoff-based feedback-that is, when players only get to observe the payoffs of their chosen actions.

引用

页码：914 / 941

页数：28

共 50 条

[41] Decentralized Dictionary Learning Over Time-Varying Digraphs
Daneshmand, Amir
Sun, Ying
Scutari, Gesualdo
Facchinei, Francisco
Sadler, Brian M.
JOURNAL OF MACHINE LEARNING RESEARCH, 2019, 20
[42] Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraints
Ribero, Monica
Vikalo, Haris
de Veciana, Gustavo
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2023, 17 (01) : 98 - 111
[43] Time-varying learning rate for recurrent neural networks to solve linear equations
Chen, Yuhuan
Chen, Jingjing
Yi, Chengfu
MATHEMATICAL METHODS IN THE APPLIED SCIENCES, 2022,
[44] Zhang neural network for online solution of time-varying convex quadratic program subject to time-varying linear-equality constraints
Zhang, Yunong
Li, Zhan
PHYSICS LETTERS A, 2009, 373 (18-19) : 1639 - 1643
[45] Optimal Iterative Learning Control for Batch Processes in the Presence of Time-Varying Dynamics
Lu, Jingyi
Cao, Zhixing
Hu, Qinran
Xu, Zuhua
Du, Wenli
Gao, Furong
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2022, 52 (01): : 680 - 692
[46] Time-varying partitioning for predictive control design: Density-games approach
Barreiro-Gomez, Julian
Ocampo-Martinez, Carlos
Quijano, Nicanor
JOURNAL OF PROCESS CONTROL, 2019, 75 : 1 - 14
[47] Distributed Seeking of Time-Varying Nash Equilibrium for Non-Cooperative Games
Ye, Maojiao
Hu, Guoqiang
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2015, 60 (11) : 3000 - 3005
[48] Distributed algorithms with linear convergence for aggregative games over time-varying networks
Zhu, Rui
Wang, Fuyong
Liu, Zhongxin
Chen, Zengqiang
EXPERT SYSTEMS WITH APPLICATIONS, 2025, 273
[49] Adaptive Fuzzy Fixed Time Time-Varying Formation Control for Heterogeneous Multiagent Systems With Full State Constraints
Hou, Han-Qian
Liu, Yan-Jun
Lan, Jie
Liu, Lei
IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2023, 31 (04) : 1152 - 1162
[50] An Online Newton's Method for Time-Varying Linear Equality Constraints
Lupien, Jean-Luc
Lesage-Landry, Antoine
IEEE CONTROL SYSTEMS LETTERS, 2023, 7 : 1423 - 1428

← 1 2 3 4 5 →