Distributed learning in a multi-agent potential game

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

In a non-cooperative dynamic game, each player participating in a changing environment aims to optimize its actions selfishly. In this paper, we focus our analysis on a class of games, namely dynamic potential game in multiagent systems. The problems of the game with constraints and without constraints are both considered; in both cases, we propose algorithms to learn the Nash equilibrium (NE) in a distributed fashion. The idea of NE learning is relied on two-time-scale dynamics and convex optimization. A numerical example is presented to verify the effectiveness of the proposed methods.

Original languageEnglish
Title of host publicationICCAS 2017 - 2017 17th International Conference on Control, Automation and Systems - Proceedings
PublisherIEEE Computer Society
Pages266-271
Number of pages6
ISBN (Electronic)9788993215137
DOIs
StatePublished - Dec 13 2017
Event17th International Conference on Control, Automation and Systems, ICCAS 2017 - Jeju, Korea, Republic of
Duration: Oct 18 2017Oct 21 2017

Publication series

NameInternational Conference on Control, Automation and Systems
Volume2017-October
ISSN (Print)1598-7833

Conference

Conference17th International Conference on Control, Automation and Systems, ICCAS 2017
Country/TerritoryKorea, Republic of
CityJeju
Period10/18/1710/21/17

Funding

This work was supported by the Korea Electric Power Corporation through Korea Electrical Engineering & Science Research Institute under Grant R15XA03-00 and by DGIST (Daegu Gyeongbuk Institute of Science and Technology).

Keywords

  • Distributed learning
  • Distributed optimization
  • Game theory
  • Singular perturbation theory

Fingerprint

Dive into the research topics of 'Distributed learning in a multi-agent potential game'. Together they form a unique fingerprint.

Cite this