Distributed learning in large-scale multi-agent games: A modified fictitious play approach

Brian Swenson; Soummya Kar; Joao Xavier

doi:10.1109/ACSSC.2012.6489275

Distributed learning in large-scale multi-agent games: A modified fictitious play approach

Brian Swenson, Soummya Kar, Joao Xavier

Applied Research Laboratory (ARL)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

15 Scopus citations

Abstract

The paper concerns the development of distributed equilibria learning strategies in large-scale multi-agent games with repeated plays. With inter-agent information exchange being restricted to a preassigned communication graph, the paper presents a modified version of the fictitious play algorithm that relies only on local neighborhood information exchange for agent policy update. Under the assumption of identical agent utility functions that are permutation invariant, the proposed distributed algorithm leads to convergence of the networked-averaged empirical play histories to a subset of the Nash equilibria, designated as the consensus equilibria. Applications of the proposed distributed framework to strategy design problems encountered in large-scale traffic networks are discussed.

Original language	English (US)
Title of host publication	Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012
Pages	1490-1495
Number of pages	6
DOIs	https://doi.org/10.1109/ACSSC.2012.6489275
State	Published - 2012
Event	46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012 - Pacific Grove, CA, United States Duration: Nov 4 2012 → Nov 7 2012

Publication series

Name	Conference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)	1058-6393

Other

Other	46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012
Country/Territory	United States
City	Pacific Grove, CA
Period	11/4/12 → 11/7/12

All Science Journal Classification (ASJC) codes

Signal Processing
Computer Networks and Communications

Access to Document

10.1109/ACSSC.2012.6489275

Cite this

Swenson, B., Kar, S., & Xavier, J. (2012). Distributed learning in large-scale multi-agent games: A modified fictitious play approach. In Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012 (pp. 1490-1495). [6489275] (Conference Record - Asilomar Conference on Signals, Systems and Computers). https://doi.org/10.1109/ACSSC.2012.6489275

@inproceedings{4f936cdb22d54cb1964cbd198d658ea2,

title = "Distributed learning in large-scale multi-agent games: A modified fictitious play approach",

abstract = "The paper concerns the development of distributed equilibria learning strategies in large-scale multi-agent games with repeated plays. With inter-agent information exchange being restricted to a preassigned communication graph, the paper presents a modified version of the fictitious play algorithm that relies only on local neighborhood information exchange for agent policy update. Under the assumption of identical agent utility functions that are permutation invariant, the proposed distributed algorithm leads to convergence of the networked-averaged empirical play histories to a subset of the Nash equilibria, designated as the consensus equilibria. Applications of the proposed distributed framework to strategy design problems encountered in large-scale traffic networks are discussed.",

author = "Brian Swenson and Soummya Kar and Joao Xavier",

year = "2012",

doi = "10.1109/ACSSC.2012.6489275",

language = "English (US)",

isbn = "9781467350518",

series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",

pages = "1490--1495",

booktitle = "Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012",

note = "46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012 ; Conference date: 04-11-2012 Through 07-11-2012",

}

Swenson, B, Kar, S & Xavier, J 2012, Distributed learning in large-scale multi-agent games: A modified fictitious play approach. in Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012., 6489275, Conference Record - Asilomar Conference on Signals, Systems and Computers, pp. 1490-1495, 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012, Pacific Grove, CA, United States, 11/4/12. https://doi.org/10.1109/ACSSC.2012.6489275

Distributed learning in large-scale multi-agent games: A modified fictitious play approach. / Swenson, Brian; Kar, Soummya; Xavier, Joao.
Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012. 2012. p. 1490-1495 6489275 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Distributed learning in large-scale multi-agent games

T2 - 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012

AU - Swenson, Brian

AU - Kar, Soummya

AU - Xavier, Joao

PY - 2012

Y1 - 2012

N2 - The paper concerns the development of distributed equilibria learning strategies in large-scale multi-agent games with repeated plays. With inter-agent information exchange being restricted to a preassigned communication graph, the paper presents a modified version of the fictitious play algorithm that relies only on local neighborhood information exchange for agent policy update. Under the assumption of identical agent utility functions that are permutation invariant, the proposed distributed algorithm leads to convergence of the networked-averaged empirical play histories to a subset of the Nash equilibria, designated as the consensus equilibria. Applications of the proposed distributed framework to strategy design problems encountered in large-scale traffic networks are discussed.

AB - The paper concerns the development of distributed equilibria learning strategies in large-scale multi-agent games with repeated plays. With inter-agent information exchange being restricted to a preassigned communication graph, the paper presents a modified version of the fictitious play algorithm that relies only on local neighborhood information exchange for agent policy update. Under the assumption of identical agent utility functions that are permutation invariant, the proposed distributed algorithm leads to convergence of the networked-averaged empirical play histories to a subset of the Nash equilibria, designated as the consensus equilibria. Applications of the proposed distributed framework to strategy design problems encountered in large-scale traffic networks are discussed.

UR - http://www.scopus.com/inward/record.url?scp=84876269571&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876269571&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2012.6489275

DO - 10.1109/ACSSC.2012.6489275

M3 - Conference contribution

AN - SCOPUS:84876269571

SN - 9781467350518

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 1490

EP - 1495

BT - Conference Record of the 46th Asilomar Conference on Signals, Systems and Computers, ASILOMAR 2012

Y2 - 4 November 2012 through 7 November 2012

ER -

Distributed learning in large-scale multi-agent games: A modified fictitious play approach

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this