RVσ(t)

A unifying approach to performance and convergence in online multiagent learning

Bikramjit Banerjee, Jing Peng

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

3 Citations (Scopus)

Abstract

We present a new multiagent learning algorithm (RVσ(t)) that can guarantee both no-regret performance (all games) and policy convergence (some games of arbitrary size). Unlike its predecessor ReDVaLeR, it (1) does not need to distinguish whether its opponents are self-play or otherwise non-stationary, (2) is allowed to know its portion of any equilibrium that, we argue, leads to convergence in some games in addition to no-regret. Although the regret of RVσ(t) is analyzed in continuous time, we show that it grows slower than in other no-regret techniques like GIGA and GIGA-WoLF. We show that RVσ(t) can converge to coordinated behavior in coordination games, while GIGA, GIGA-WoLF may converge to poorly coordinated (mixed) behaviors.

Original languageEnglish
Title of host publicationProceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems
Pages798-800
Number of pages3
Volume2006
DOIs
StatePublished - 1 Dec 2006
EventFifth International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS - Hakodate, Japan
Duration: 8 May 200612 May 2006

Other

OtherFifth International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
CountryJapan
CityHakodate
Period8/05/0612/05/06

Fingerprint

Learning algorithms

Keywords

  • Game theory
  • Multiagent learning

Cite this

Banerjee, B., & Peng, J. (2006). RVσ(t): A unifying approach to performance and convergence in online multiagent learning. In Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems (Vol. 2006, pp. 798-800) https://doi.org/10.1145/1160633.1160775
Banerjee, Bikramjit ; Peng, Jing. / RVσ(t) : A unifying approach to performance and convergence in online multiagent learning. Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems. Vol. 2006 2006. pp. 798-800
@inproceedings{bb432dfddc724657b058bd490d6c235e,
title = "RVσ(t): A unifying approach to performance and convergence in online multiagent learning",
abstract = "We present a new multiagent learning algorithm (RVσ(t)) that can guarantee both no-regret performance (all games) and policy convergence (some games of arbitrary size). Unlike its predecessor ReDVaLeR, it (1) does not need to distinguish whether its opponents are self-play or otherwise non-stationary, (2) is allowed to know its portion of any equilibrium that, we argue, leads to convergence in some games in addition to no-regret. Although the regret of RVσ(t) is analyzed in continuous time, we show that it grows slower than in other no-regret techniques like GIGA and GIGA-WoLF. We show that RVσ(t) can converge to coordinated behavior in coordination games, while GIGA, GIGA-WoLF may converge to poorly coordinated (mixed) behaviors.",
keywords = "Game theory, Multiagent learning",
author = "Bikramjit Banerjee and Jing Peng",
year = "2006",
month = "12",
day = "1",
doi = "10.1145/1160633.1160775",
language = "English",
isbn = "1595933034",
volume = "2006",
pages = "798--800",
booktitle = "Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems",

}

Banerjee, B & Peng, J 2006, RVσ(t): A unifying approach to performance and convergence in online multiagent learning. in Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems. vol. 2006, pp. 798-800, Fifth International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, Hakodate, Japan, 8/05/06. https://doi.org/10.1145/1160633.1160775

RVσ(t) : A unifying approach to performance and convergence in online multiagent learning. / Banerjee, Bikramjit; Peng, Jing.

Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems. Vol. 2006 2006. p. 798-800.

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

TY - GEN

T1 - RVσ(t)

T2 - A unifying approach to performance and convergence in online multiagent learning

AU - Banerjee, Bikramjit

AU - Peng, Jing

PY - 2006/12/1

Y1 - 2006/12/1

N2 - We present a new multiagent learning algorithm (RVσ(t)) that can guarantee both no-regret performance (all games) and policy convergence (some games of arbitrary size). Unlike its predecessor ReDVaLeR, it (1) does not need to distinguish whether its opponents are self-play or otherwise non-stationary, (2) is allowed to know its portion of any equilibrium that, we argue, leads to convergence in some games in addition to no-regret. Although the regret of RVσ(t) is analyzed in continuous time, we show that it grows slower than in other no-regret techniques like GIGA and GIGA-WoLF. We show that RVσ(t) can converge to coordinated behavior in coordination games, while GIGA, GIGA-WoLF may converge to poorly coordinated (mixed) behaviors.

AB - We present a new multiagent learning algorithm (RVσ(t)) that can guarantee both no-regret performance (all games) and policy convergence (some games of arbitrary size). Unlike its predecessor ReDVaLeR, it (1) does not need to distinguish whether its opponents are self-play or otherwise non-stationary, (2) is allowed to know its portion of any equilibrium that, we argue, leads to convergence in some games in addition to no-regret. Although the regret of RVσ(t) is analyzed in continuous time, we show that it grows slower than in other no-regret techniques like GIGA and GIGA-WoLF. We show that RVσ(t) can converge to coordinated behavior in coordination games, while GIGA, GIGA-WoLF may converge to poorly coordinated (mixed) behaviors.

KW - Game theory

KW - Multiagent learning

UR - http://www.scopus.com/inward/record.url?scp=34247189601&partnerID=8YFLogxK

U2 - 10.1145/1160633.1160775

DO - 10.1145/1160633.1160775

M3 - Conference contribution

SN - 1595933034

SN - 9781595933034

VL - 2006

SP - 798

EP - 800

BT - Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems

ER -

Banerjee B, Peng J. RVσ(t): A unifying approach to performance and convergence in online multiagent learning. In Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems. Vol. 2006. 2006. p. 798-800 https://doi.org/10.1145/1160633.1160775