Coordinated exploration in conflicting multi-stage games

Maarten Peeters; Ville Könönen; Katja Verbeeck; Sven van Segbroeck; Ann Nowé

doi:10.1007/978-3-540-85565-1_49

Coordinated exploration in conflicting multi-stage games

Maarten Peeters, Ville Könönen, Katja Verbeeck, Sven van Segbroeck, Ann Nowé

VTT Technical Research Centre of Finland

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

The analysis of the collective behavior of agents in a distributed multi-agent environment received a lot of attention in the past decade. More accurately, coordination was studied intensely because it enables agents to converge to Pareto optimal solutions and Nash equilibria. Most of these studies focussed on team games. In this paper we report on a technique for finding fair solutions in conflicting interest multi-stage games. Our hierarchical periodic policies algorithm is based on the characteristics of a homo egualis society in which the players also care about the proportional distribution of the pay-off in relation to the pay-off of the other players. This feature is built into a hierarchy of learning automata which is suited for playing sequential decision problems.

Original language	English
Title of host publication	Knowledge-Based Intelligent Information and Engineering Systems
Subtitle of host publication	12th International Conference, KES 2008
Editors	Ignic Lovrek, Robert J. Howlett, Lakhmi C. Jain
Place of Publication	Heidelberg
Publisher	Springer
Pages	391-402
Volume	II
ISBN (Print)	978-3-540-85564-4
DOIs	https://doi.org/10.1007/978-3-540-85565-1_49
Publication status	Published - 2008
MoE publication type	A4 Article in a conference publication
Event	12th International Conference on Knowledge-Based Intelligent Information and Engineering Systems, KES-2008 - Zagreb, Croatia Duration: 3 Sept 2008 → 5 Sept 2008 Conference number: 12

Publication series

Series	Lecture Notes in Computer Science
Volume	5178
ISSN	0302-9743

Conference

Conference	12th International Conference on Knowledge-Based Intelligent Information and Engineering Systems, KES-2008
Abbreviated title	KES-2008
Country/Territory	Croatia
City	Zagreb
Period	3/09/08 → 5/09/08

Keywords

Learning automata
reinforcement learning
policy gradient
multi-agent systems
exploration

Access to Document

10.1007/978-3-540-85565-1_49

Cite this

Peeters, M., Könönen, V., Verbeeck, K., van Segbroeck, S., & Nowé, A. (2008). Coordinated exploration in conflicting multi-stage games. In I. Lovrek, R. J. Howlett, & L. C. Jain (Eds.), Knowledge-Based Intelligent Information and Engineering Systems: 12th International Conference, KES 2008 (Vol. II, pp. 391-402). Springer. Lecture Notes in Computer Science Vol. 5178 https://doi.org/10.1007/978-3-540-85565-1_49

Peeters, Maarten ; Könönen, Ville ; Verbeeck, Katja et al. / Coordinated exploration in conflicting multi-stage games. Knowledge-Based Intelligent Information and Engineering Systems: 12th International Conference, KES 2008. editor / Ignic Lovrek ; Robert J. Howlett ; Lakhmi C. Jain. Vol. II Heidelberg : Springer, 2008. pp. 391-402 (Lecture Notes in Computer Science, Vol. 5178).

@inproceedings{9fcab082dfdb4b0fab35da08e91bee2a,

title = "Coordinated exploration in conflicting multi-stage games",

abstract = "The analysis of the collective behavior of agents in a distributed multi-agent environment received a lot of attention in the past decade. More accurately, coordination was studied intensely because it enables agents to converge to Pareto optimal solutions and Nash equilibria. Most of these studies focussed on team games. In this paper we report on a technique for finding fair solutions in conflicting interest multi-stage games. Our hierarchical periodic policies algorithm is based on the characteristics of a homo egualis society in which the players also care about the proportional distribution of the pay-off in relation to the pay-off of the other players. This feature is built into a hierarchy of learning automata which is suited for playing sequential decision problems.",

keywords = "Learning automata, reinforcement learning, policy gradient, multi-agent systems, exploration",

author = "Maarten Peeters and Ville K{\"o}n{\"o}nen and Katja Verbeeck and {van Segbroeck}, Sven and Ann Now{\'e}",

year = "2008",

doi = "10.1007/978-3-540-85565-1_49",

language = "English",

isbn = "978-3-540-85564-4",

volume = "II",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "391--402",

editor = "Ignic Lovrek and Howlett, {Robert J.} and Jain, {Lakhmi C.}",

booktitle = "Knowledge-Based Intelligent Information and Engineering Systems",

address = "Germany",

note = "12th International Conference on Knowledge-Based Intelligent Information and Engineering Systems, KES-2008, KES-2008 ; Conference date: 03-09-2008 Through 05-09-2008",

}

Peeters, M, Könönen, V, Verbeeck, K, van Segbroeck, S & Nowé, A 2008, Coordinated exploration in conflicting multi-stage games. in I Lovrek, RJ Howlett & LC Jain (eds), Knowledge-Based Intelligent Information and Engineering Systems: 12th International Conference, KES 2008. vol. II, Springer, Heidelberg, Lecture Notes in Computer Science, vol. 5178, pp. 391-402, 12th International Conference on Knowledge-Based Intelligent Information and Engineering Systems, KES-2008, Zagreb, Croatia, 3/09/08. https://doi.org/10.1007/978-3-540-85565-1_49

Coordinated exploration in conflicting multi-stage games. / Peeters, Maarten; Könönen, Ville; Verbeeck, Katja et al.

Knowledge-Based Intelligent Information and Engineering Systems: 12th International Conference, KES 2008. ed. / Ignic Lovrek; Robert J. Howlett; Lakhmi C. Jain. Vol. II Heidelberg : Springer, 2008. p. 391-402 (Lecture Notes in Computer Science, Vol. 5178).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Coordinated exploration in conflicting multi-stage games

AU - Peeters, Maarten

AU - Könönen, Ville

AU - Verbeeck, Katja

AU - van Segbroeck, Sven

AU - Nowé, Ann

N1 - Conference code: 12

PY - 2008

Y1 - 2008

N2 - The analysis of the collective behavior of agents in a distributed multi-agent environment received a lot of attention in the past decade. More accurately, coordination was studied intensely because it enables agents to converge to Pareto optimal solutions and Nash equilibria. Most of these studies focussed on team games. In this paper we report on a technique for finding fair solutions in conflicting interest multi-stage games. Our hierarchical periodic policies algorithm is based on the characteristics of a homo egualis society in which the players also care about the proportional distribution of the pay-off in relation to the pay-off of the other players. This feature is built into a hierarchy of learning automata which is suited for playing sequential decision problems.

AB - The analysis of the collective behavior of agents in a distributed multi-agent environment received a lot of attention in the past decade. More accurately, coordination was studied intensely because it enables agents to converge to Pareto optimal solutions and Nash equilibria. Most of these studies focussed on team games. In this paper we report on a technique for finding fair solutions in conflicting interest multi-stage games. Our hierarchical periodic policies algorithm is based on the characteristics of a homo egualis society in which the players also care about the proportional distribution of the pay-off in relation to the pay-off of the other players. This feature is built into a hierarchy of learning automata which is suited for playing sequential decision problems.

KW - Learning automata

KW - reinforcement learning

KW - policy gradient

KW - multi-agent systems

KW - exploration

U2 - 10.1007/978-3-540-85565-1_49

DO - 10.1007/978-3-540-85565-1_49

M3 - Conference article in proceedings

SN - 978-3-540-85564-4

VL - II

T3 - Lecture Notes in Computer Science

SP - 391

EP - 402

BT - Knowledge-Based Intelligent Information and Engineering Systems

A2 - Lovrek, Ignic

A2 - Howlett, Robert J.

A2 - Jain, Lakhmi C.

PB - Springer

CY - Heidelberg

T2 - 12th International Conference on Knowledge-Based Intelligent Information and Engineering Systems, KES-2008

Y2 - 3 September 2008 through 5 September 2008

ER -

Peeters M, Könönen V, Verbeeck K, van Segbroeck S, Nowé A. Coordinated exploration in conflicting multi-stage games. In Lovrek I, Howlett RJ, Jain LC, editors, Knowledge-Based Intelligent Information and Engineering Systems: 12th International Conference, KES 2008. Vol. II. Heidelberg: Springer. 2008. p. 391-402. (Lecture Notes in Computer Science, Vol. 5178). doi: 10.1007/978-3-540-85565-1_49

Coordinated exploration in conflicting multi-stage games

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this