Strategic capability-learning for improved multi-agent collaboration in ad-hoc environments

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

Abstract

We consider the problem of distributed collaboration among multiple agents to perform tasks in an ad-hoc setting. Because the setting is ad-hoc, the agents could be programmed by different people and could potentially have different task selection and task execution algorithms. We consider the problem of decision making by the agents within such an ad-hoc setting so that the overall utility of the agent society can be improved. In this paper we describe an ad-hoc collaboration framework where each agent strategically selects capabilities to learn from other agents which would help it to improve its expected future utility of performing tasks. Agents use a very flexible, blackboard-based architecture to coordinate operations with each other and model the dynamic nature of tasks and agents in the environment using two 'openness' parameters. Experimental results within the Repast agent simulator show that by using the appropriate learning strategy, the overall utility of the agents improves considerably.

Original languageEnglish (US)
Title of host publicationProceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012
Pages287-292
Number of pages6
DOIs
StatePublished - Dec 1 2012
Event2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012 - Macau, China
Duration: Dec 4 2012Dec 7 2012

Publication series

NameProceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012
Volume2

Conference

Conference2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012
CountryChina
CityMacau
Period12/4/1212/7/12

Fingerprint

Simulators
Decision making

Keywords

  • ad-hoc
  • collaboration
  • learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Jumadinova, J., Dasgupta, P., & Soh, L-K. (2012). Strategic capability-learning for improved multi-agent collaboration in ad-hoc environments. In Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012 (pp. 287-292). [6511583] (Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012; Vol. 2). https://doi.org/10.1109/WI-IAT.2012.57

Strategic capability-learning for improved multi-agent collaboration in ad-hoc environments. / Jumadinova, Janyl; Dasgupta, Prithviraj; Soh, Leen-Kiat.

Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012. 2012. p. 287-292 6511583 (Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012; Vol. 2).

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

Jumadinova, J, Dasgupta, P & Soh, L-K 2012, Strategic capability-learning for improved multi-agent collaboration in ad-hoc environments. in Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012., 6511583, Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012, vol. 2, pp. 287-292, 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012, Macau, China, 12/4/12. https://doi.org/10.1109/WI-IAT.2012.57
Jumadinova J, Dasgupta P, Soh L-K. Strategic capability-learning for improved multi-agent collaboration in ad-hoc environments. In Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012. 2012. p. 287-292. 6511583. (Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012). https://doi.org/10.1109/WI-IAT.2012.57
Jumadinova, Janyl ; Dasgupta, Prithviraj ; Soh, Leen-Kiat. / Strategic capability-learning for improved multi-agent collaboration in ad-hoc environments. Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012. 2012. pp. 287-292 (Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012).
@inproceedings{ee3b6d46fa7f48c4ab8f1c8fb0cf8b4a,
title = "Strategic capability-learning for improved multi-agent collaboration in ad-hoc environments",
abstract = "We consider the problem of distributed collaboration among multiple agents to perform tasks in an ad-hoc setting. Because the setting is ad-hoc, the agents could be programmed by different people and could potentially have different task selection and task execution algorithms. We consider the problem of decision making by the agents within such an ad-hoc setting so that the overall utility of the agent society can be improved. In this paper we describe an ad-hoc collaboration framework where each agent strategically selects capabilities to learn from other agents which would help it to improve its expected future utility of performing tasks. Agents use a very flexible, blackboard-based architecture to coordinate operations with each other and model the dynamic nature of tasks and agents in the environment using two 'openness' parameters. Experimental results within the Repast agent simulator show that by using the appropriate learning strategy, the overall utility of the agents improves considerably.",
keywords = "ad-hoc, collaboration, learning",
author = "Janyl Jumadinova and Prithviraj Dasgupta and Leen-Kiat Soh",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/WI-IAT.2012.57",
language = "English (US)",
isbn = "9780769548807",
series = "Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012",
pages = "287--292",
booktitle = "Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012",

}

TY - GEN

T1 - Strategic capability-learning for improved multi-agent collaboration in ad-hoc environments

AU - Jumadinova, Janyl

AU - Dasgupta, Prithviraj

AU - Soh, Leen-Kiat

PY - 2012/12/1

Y1 - 2012/12/1

N2 - We consider the problem of distributed collaboration among multiple agents to perform tasks in an ad-hoc setting. Because the setting is ad-hoc, the agents could be programmed by different people and could potentially have different task selection and task execution algorithms. We consider the problem of decision making by the agents within such an ad-hoc setting so that the overall utility of the agent society can be improved. In this paper we describe an ad-hoc collaboration framework where each agent strategically selects capabilities to learn from other agents which would help it to improve its expected future utility of performing tasks. Agents use a very flexible, blackboard-based architecture to coordinate operations with each other and model the dynamic nature of tasks and agents in the environment using two 'openness' parameters. Experimental results within the Repast agent simulator show that by using the appropriate learning strategy, the overall utility of the agents improves considerably.

AB - We consider the problem of distributed collaboration among multiple agents to perform tasks in an ad-hoc setting. Because the setting is ad-hoc, the agents could be programmed by different people and could potentially have different task selection and task execution algorithms. We consider the problem of decision making by the agents within such an ad-hoc setting so that the overall utility of the agent society can be improved. In this paper we describe an ad-hoc collaboration framework where each agent strategically selects capabilities to learn from other agents which would help it to improve its expected future utility of performing tasks. Agents use a very flexible, blackboard-based architecture to coordinate operations with each other and model the dynamic nature of tasks and agents in the environment using two 'openness' parameters. Experimental results within the Repast agent simulator show that by using the appropriate learning strategy, the overall utility of the agents improves considerably.

KW - ad-hoc

KW - collaboration

KW - learning

UR - http://www.scopus.com/inward/record.url?scp=84878424827&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878424827&partnerID=8YFLogxK

U2 - 10.1109/WI-IAT.2012.57

DO - 10.1109/WI-IAT.2012.57

M3 - Conference contribution

SN - 9780769548807

T3 - Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012

SP - 287

EP - 292

BT - Proceedings - 2012 IEEE/WIC/ACM International Conference on Intelligent Agent Technology, IAT 2012

ER -