Social comparison for failure detection and recovery in multi-agent settings

Gal A. Kaminka, Milind Tambe

Research output: Contribution to conferencePaperpeer-review

Abstract

A novel approach to failure detection that is based on ideas from Social Comparison Theory is proposed. In this approach, agents use their team-mates as sources of information on the situation and the ideal behavior. The agents compare their own goals and plans to those of the other team members, in order to detect failures and correct their behavior. The proposed approach has been implemented in Soar.

Original languageEnglish
Pages834
Number of pages1
StatePublished - 1997
Externally publishedYes
EventProceedings of the 1997 14th National Conference on Artificial Intelligence, AAAI 97 - Providence, RI, USA
Duration: 27 Jul 199731 Jul 1997

Conference

ConferenceProceedings of the 1997 14th National Conference on Artificial Intelligence, AAAI 97
CityProvidence, RI, USA
Period27/07/9731/07/97

Fingerprint

Dive into the research topics of 'Social comparison for failure detection and recovery in multi-agent settings'. Together they form a unique fingerprint.

Cite this