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

[31] Time-Varying Group Formation Tracking for Multiagent Systems With Competition and Cooperation via Distributed Nash Equilibrium Seeking
Hu, Chenxi
Hua, Yongzhao
Dong, Xiwang
Yu, Jianglong
Lu, Jinhu
Ren, Zhang
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2024, 20 (08) : 10054 - 10064
[32] Consensus of Multiagent Systems With Time-Varying Input Delay via Truncated Predictor Feedback
Chu, Hongjun
Yue, Dong
Dou, Chunxia
Xie, Xiangpeng
Chu, Lanling
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2021, 51 (10): : 6062 - 6073
[33] Convergence to Zero of Quadratic Lyapunov Functions for Multiagent Systems in Time-Varying Directed Networks
Wang, Bo
Tian, Yu-Ping
Han, Zhimin
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2023, 68 (12) : 8178 - 8184
[34] A New Varying-Parameter Design Formula for Solving Time-Varying Problems
Stanimirovic, Predrag S.
Katsikis, Vasilios N.
Gerontitis, Dimitrios
NEURAL PROCESSING LETTERS, 2021, 53 (01) : 107 - 129
[35] Consensus of Multiagent Systems With Time-Varying Input Delay and Relative State Saturation Constraints
Chu, Hongjun
Yue, Dong
Dou, Chunxia
Chu, Lanling
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2021, 51 (11): : 6938 - 6944
[36] Robustness Analysis of Asynchronous Sampled-Data Multiagent Networks With Time-Varying Delays
Xiao, Feng
Shi, Yang
Ren, Wei
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2018, 63 (07) : 2145 - 2152
[37] Time-Varying Optimal Formation Control for Second-Order Multiagent Systems Based on Neural Network Observer and Reinforcement Learning
Lan, Jie
Liu, Yan-Jun
Yu, Dengxiu
Wen, Guoxing
Tong, Shaocheng
Liu, Lei
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (03) : 3144 - 3155
[38] Manifold learning for fMRI time-varying functional connectivity
Gonzalez-Castillo, Javier
Fernandez, Isabel S. S.
Lam, Ka Chun
Handwerker, Daniel A. A.
Pereira, Francisco
Bandettini, Peter A. A.
FRONTIERS IN HUMAN NEUROSCIENCE, 2023, 17
[39] Sparsity Learning Formulations for Mining Time-Varying Data
Li, Rongjian
Zhang, Wenlu
Zhao, Yao
Zhu, Zhenfeng
Ji, Shuiwang
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2015, 27 (05) : 1411 - 1423
[40] Learning Identification of a Class of Time-Varying ARMAX Systems
Sun Mingxuan
Chen Baixia
Bi Hongbo
PROCEEDINGS OF THE 31ST CHINESE CONTROL CONFERENCE, 2012, : 1860 - 1865

← 1 2 3 4 5 →