Learning efficient correlated equilibria

Handle URI:
http://hdl.handle.net/10754/550513
Title:
Learning efficient correlated equilibria
Authors:
Borowski, Holly P.; Marden, Jason R.; Shamma, Jeff S. ( 0000-0001-5638-9551 )
Abstract:
The majority of distributed learning literature focuses on convergence to Nash equilibria. Correlated equilibria, on the other hand, can often characterize more efficient collective behavior than even the best Nash equilibrium. However, there are no existing distributed learning algorithms that converge to specific correlated equilibria. In this paper, we provide one such algorithm which guarantees that the agents' collective joint strategy will constitute an efficient correlated equilibrium with high probability. The key to attaining efficient correlated behavior through distributed learning involves incorporating a common random signal into the learning environment.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
IEEE
Journal:
Decision and Control (CDC), 2014 IEEE 53rd Annual Conference on
Conference/Event name:
2014 53rd IEEE Annual Conference on Decision and Control, CDC 2014
Issue Date:
15-Dec-2014
DOI:
10.1109/CDC.2014.7040463
Type:
Conference Paper
Additional Links:
http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7040463
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorBorowski, Holly P.en
dc.contributor.authorMarden, Jason R.en
dc.contributor.authorShamma, Jeff S.en
dc.date.accessioned2015-04-23T14:14:23Zen
dc.date.available2015-04-23T14:14:23Zen
dc.date.issued2014-12-15en
dc.identifier.doi10.1109/CDC.2014.7040463en
dc.identifier.urihttp://hdl.handle.net/10754/550513en
dc.description.abstractThe majority of distributed learning literature focuses on convergence to Nash equilibria. Correlated equilibria, on the other hand, can often characterize more efficient collective behavior than even the best Nash equilibrium. However, there are no existing distributed learning algorithms that converge to specific correlated equilibria. In this paper, we provide one such algorithm which guarantees that the agents' collective joint strategy will constitute an efficient correlated equilibrium with high probability. The key to attaining efficient correlated behavior through distributed learning involves incorporating a common random signal into the learning environment.en
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7040463en
dc.rights(c) 2014 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.en
dc.titleLearning efficient correlated equilibriaen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalDecision and Control (CDC), 2014 IEEE 53rd Annual Conference onen
dc.conference.date15 December 2014 through 17 December 2014en
dc.conference.name2014 53rd IEEE Annual Conference on Decision and Control, CDC 2014en
dc.eprint.versionPost-printen
dc.contributor.institutionDepartment of Aerospace Engineering, University of Colorado, Boulderen
dc.contributor.institutionDepartment of Electrical, Computer, and Energy Engineering, University of Colorado, Boulderen
kaust.authorShamma, Jeff S.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.