A Multiagent System Manages Collaboration in Emergent Processes

UTSePress Research/Manakin Repository

Search UTSePress Research

Advanced Search


My Account

Show simple item record

dc.contributor.author Debenham, John en_US
dc.contributor.editor Dignum, F; Dignum, V; Koenig, S; Kraus, S; Singh, M; Wooldridge, M en_US
dc.date.accessioned 2010-05-18T06:49:40Z
dc.date.available 2010-05-18T06:49:40Z
dc.date.issued 2005 en_US
dc.identifier 2005002923 en_US
dc.identifier.citation Debenham John 2005, 'A Multiagent System Manages Collaboration in Emergent Processes', ACM, New York, USA, pp. 175-182. en_US
dc.identifier.issn 1-59593-094-9 en_US
dc.identifier.other E1 en_US
dc.identifier.uri http://hdl.handle.net/10453/7077
dc.description.abstract Emergent processes are non-routine, collaborative business processes whose execution is guided by the knowledge that emerges during a process instance. In so far as the process goal gives direction to conventional business processes, the continually evolving process knowledge gives direction to emergent processes. Emergent processes may involve informal interaction, and so there is a limit to the extent to which the processes can be "managed". The collaboration however can be managed. Managing collaboration needs an intelligent agent that is guided not by a process goal, but by observing the performance of the other agents. Each agent has process knowledge --- that is information either generated by the individual users or is extracted from the environment, and performance knowledge --- that describes how the other agents, together with their 'owners', perform --- including how reliable they are. The integrity of the information derived from past observations decays in time, and so they have an inference mechanism that can cope with information of decaying integrity. An agent is described that achieves this by using ideas from information theory. The agents' internal representation language is probabilistic first-order logic. They derive models of the other agents using entropy-based inference that is based on random worlds. Maximum entropy inference is used to construct these models that are then refreshed as new information is received using minimum relative entropy inference. en_US
dc.publisher ACM en_US
dc.relation.hasversion Accepted manuscript version en_US
dc.relation.isbasedon http://dx.doi.org/10.1145/1082473.1082500 en_US
dc.rights "© ACM 2005. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in: AAMAS '05 Proceedings of the fourth international joint conference on Autonomous agents and multiagent systems. http://doi.acm.org/10.1145/1082473.1082500 " en_US
dc.title A Multiagent System Manages Collaboration in Emergent Processes en_US
dc.parent Proceedings of the Fourth International Joint Conference on Autonomous Agents and Multiagent Systems en_US
dc.journal.volume en_US
dc.journal.number en_US
dc.publocation New York, USA en_US
dc.identifier.startpage 175 en_US
dc.identifier.endpage 182 en_US
dc.cauo.name FEIT.School of Software en_US
dc.conference en_US
dc.conference Verified OK en_US
dc.conference.location Utrecht, Netherlands en_US
dc.for 080109 en_US
dc.personcode 723535 en_US
dc.percentage 100 en_US
dc.classification.name Pattern Recognition and Data Mining en_US
dc.classification.type FOR-08 en_US
dc.custom International Conference on Autonomous Agents and Multiagent Systems en_US
dc.date.activity 20050725 en_US
dc.location.activity Utrecht, Netherlands en_US
dc.description.keywords agent en_US
dc.staffid 723535 en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record