Learning how to plan and instantiate a plan in multi-agent coalition formation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

We propose an innovative two-step learning approach to planning- instantiation for multi-agent coalition formation in dynamic, uncertain, real-time, and noisy environments. The first step teams about the planning of a coalition to improve its quality, adapting to the real-time and environmental requirements. The second step learns about the instantiation of the plan to improve the formation process, taking into account uncertain and dynamic behaviors of the peer agents. Decomposing the approach into two steps allows for modularity and flexibility in learning: learning how to plan a coalition is strategic while learning how to instantiate a plan is tactical. Our approach employs a case-based reinforcement learning (CBRL) framework.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Systems. IAT 2004
EditorsN. Zhong, J. Bradshaw, S.K. Pal, D. Talia, J. Liu, N. Cercone
Pages479-482
Number of pages4
StatePublished - Dec 1 2004
EventProceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Technology. IAT 2004 - Beijing, China
Duration: Sep 20 2004Sep 24 2004

Publication series

NameProceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Technology. IAT 2004

Conference

ConferenceProceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Technology. IAT 2004
CountryChina
CityBeijing
Period9/20/049/24/04

Fingerprint

Planning
Reinforcement learning

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Li, X., & Soh, L-K. (2004). Learning how to plan and instantiate a plan in multi-agent coalition formation. In N. Zhong, J. Bradshaw, S. K. Pal, D. Talia, J. Liu, & N. Cercone (Eds.), Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Systems. IAT 2004 (pp. 479-482). (Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Technology. IAT 2004).

Learning how to plan and instantiate a plan in multi-agent coalition formation. / Li, Xin; Soh, Leen-Kiat.

Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Systems. IAT 2004. ed. / N. Zhong; J. Bradshaw; S.K. Pal; D. Talia; J. Liu; N. Cercone. 2004. p. 479-482 (Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Technology. IAT 2004).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, X & Soh, L-K 2004, Learning how to plan and instantiate a plan in multi-agent coalition formation. in N Zhong, J Bradshaw, SK Pal, D Talia, J Liu & N Cercone (eds), Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Systems. IAT 2004. Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Technology. IAT 2004, pp. 479-482, Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Technology. IAT 2004, Beijing, China, 9/20/04.
Li X, Soh L-K. Learning how to plan and instantiate a plan in multi-agent coalition formation. In Zhong N, Bradshaw J, Pal SK, Talia D, Liu J, Cercone N, editors, Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Systems. IAT 2004. 2004. p. 479-482. (Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Technology. IAT 2004).
Li, Xin ; Soh, Leen-Kiat. / Learning how to plan and instantiate a plan in multi-agent coalition formation. Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Systems. IAT 2004. editor / N. Zhong ; J. Bradshaw ; S.K. Pal ; D. Talia ; J. Liu ; N. Cercone. 2004. pp. 479-482 (Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Technology. IAT 2004).
@inproceedings{7e1fe4cbbd5b400b864bf7b19b4b116f,
title = "Learning how to plan and instantiate a plan in multi-agent coalition formation",
abstract = "We propose an innovative two-step learning approach to planning- instantiation for multi-agent coalition formation in dynamic, uncertain, real-time, and noisy environments. The first step teams about the planning of a coalition to improve its quality, adapting to the real-time and environmental requirements. The second step learns about the instantiation of the plan to improve the formation process, taking into account uncertain and dynamic behaviors of the peer agents. Decomposing the approach into two steps allows for modularity and flexibility in learning: learning how to plan a coalition is strategic while learning how to instantiate a plan is tactical. Our approach employs a case-based reinforcement learning (CBRL) framework.",
author = "Xin Li and Leen-Kiat Soh",
year = "2004",
month = "12",
day = "1",
language = "English (US)",
isbn = "0769521010",
series = "Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Technology. IAT 2004",
pages = "479--482",
editor = "N. Zhong and J. Bradshaw and S.K. Pal and D. Talia and J. Liu and N. Cercone",
booktitle = "Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Systems. IAT 2004",

}

TY - GEN

T1 - Learning how to plan and instantiate a plan in multi-agent coalition formation

AU - Li, Xin

AU - Soh, Leen-Kiat

PY - 2004/12/1

Y1 - 2004/12/1

N2 - We propose an innovative two-step learning approach to planning- instantiation for multi-agent coalition formation in dynamic, uncertain, real-time, and noisy environments. The first step teams about the planning of a coalition to improve its quality, adapting to the real-time and environmental requirements. The second step learns about the instantiation of the plan to improve the formation process, taking into account uncertain and dynamic behaviors of the peer agents. Decomposing the approach into two steps allows for modularity and flexibility in learning: learning how to plan a coalition is strategic while learning how to instantiate a plan is tactical. Our approach employs a case-based reinforcement learning (CBRL) framework.

AB - We propose an innovative two-step learning approach to planning- instantiation for multi-agent coalition formation in dynamic, uncertain, real-time, and noisy environments. The first step teams about the planning of a coalition to improve its quality, adapting to the real-time and environmental requirements. The second step learns about the instantiation of the plan to improve the formation process, taking into account uncertain and dynamic behaviors of the peer agents. Decomposing the approach into two steps allows for modularity and flexibility in learning: learning how to plan a coalition is strategic while learning how to instantiate a plan is tactical. Our approach employs a case-based reinforcement learning (CBRL) framework.

UR - http://www.scopus.com/inward/record.url?scp=16244375221&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=16244375221&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0769521010

T3 - Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Technology. IAT 2004

SP - 479

EP - 482

BT - Proceedings - IEEE/WIC/ACM International Conference on Intelligent Agent Systems. IAT 2004

A2 - Zhong, N.

A2 - Bradshaw, J.

A2 - Pal, S.K.

A2 - Talia, D.

A2 - Liu, J.

A2 - Cercone, N.

ER -