Nonasymptotic mean-field games

Handle URI:
http://hdl.handle.net/10754/563897
Title:
Nonasymptotic mean-field games
Authors:
Tembine, Hamidou
Abstract:
Mean-field games have been studied under the assumption of very large number of players. For such large systems, the basic idea consists of approximating large games by a stylized game model with a continuum of players. The approach has been shown to be useful in some applications. However, the stylized game model with continuum of decision-makers is rarely observed in practice and the approximation proposed in the asymptotic regime is meaningless for networks with few entities. In this paper, we propose a mean-field framework that is suitable not only for large systems but also for a small world with few number of entities. The applicability of the proposed framework is illustrated through various examples including dynamic auction with asymmetric valuation distributions, and spiteful bidders.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
Institute of Electrical and Electronics Engineers (IEEE)
Journal:
IEEE Transactions on Cybernetics
Issue Date:
Dec-2014
DOI:
10.1109/TCYB.2014.2315171
Type:
Article
ISSN:
21682267
Appears in Collections:
Articles; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorTembine, Hamidouen
dc.date.accessioned2015-08-03T12:18:46Zen
dc.date.available2015-08-03T12:18:46Zen
dc.date.issued2014-12en
dc.identifier.issn21682267en
dc.identifier.doi10.1109/TCYB.2014.2315171en
dc.identifier.urihttp://hdl.handle.net/10754/563897en
dc.description.abstractMean-field games have been studied under the assumption of very large number of players. For such large systems, the basic idea consists of approximating large games by a stylized game model with a continuum of players. The approach has been shown to be useful in some applications. However, the stylized game model with continuum of decision-makers is rarely observed in practice and the approximation proposed in the asymptotic regime is meaningless for networks with few entities. In this paper, we propose a mean-field framework that is suitable not only for large systems but also for a small world with few number of entities. The applicability of the proposed framework is illustrated through various examples including dynamic auction with asymmetric valuation distributions, and spiteful bidders.en
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.subjectApproximationen
dc.subjectGames with few decision-makersen
dc.subjectNonasymptoticen
dc.titleNonasymptotic mean-field gamesen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalIEEE Transactions on Cyberneticsen
kaust.authorTembine, Hamidouen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.