Publication:
Distributed reinforcement learning in multi-agent decision systems

dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Planificación y Aprendizajees
dc.contributor.authorGiráldez, J. Ignacio
dc.contributor.authorBorrajo Millán, Daniel
dc.date.accessioned2010-02-17T14:16:12Z
dc.date.available2010-02-17T14:16:12Z
dc.date.issued1998-01
dc.descriptionProceeding of: 6th Ibero-American Conference on AI (IBERAMIA '98),Lisbon, Portugal, October 5–9, 1998
dc.description.abstractDecision problems can be usually solved using systems that implement different paradigms. These systems may be integrated into a single distributed system, with the expectation of obtaining a group performance more satisfactory than individual performances. Such a distributed system is what we call a Multi Agent Decision System (MADES), a special kind of Multi Agent System, that integrates several heterogeneous autonomous decision systems (agents). A MADES must produce a single solution proposal for the problem instance it faces, despite the fact that its decision making is distributed, and every agent produces solution proposals according to its local view and to its idiosyncrasy. We present a distributed reinforcement algorithm for learning how to combine the decisions the agents make in a distributed way, into a single group decision (solution proposal).
dc.description.statusPublicado
dc.format.mimetypeapplication/pdf
dc.identifier.bibliographicCitationProgress in artificial intelligence, Iberamia 98: 6th Ibero-American Conference on AI, Lisbon, Portugal, October 1998, p. 148-478
dc.identifier.doi10.1007/3-540-49795-1_13
dc.identifier.isbn978-3-540-64992-2 (Print)
dc.identifier.isbn978-3-540-49795-0 (Online)
dc.identifier.issn0302-9743 (Print)
dc.identifier.issn1611-3349 (Online)
dc.identifier.publicationfirstpage148
dc.identifier.publicationlastpage159
dc.identifier.publicationtitleProgress in artificial intelligence, Iberamia 98
dc.identifier.publicationvolume1484
dc.identifier.urihttps://hdl.handle.net/10016/6908
dc.language.isoeng
dc.publisherSpringer
dc.relation.eventdateOctober 5–9, 1998
dc.relation.eventnumber6
dc.relation.eventplaceLisbon (Portugal)
dc.relation.eventtitleIbero-American Conference on AI (IBERAMIA '98)
dc.relation.ispartofseriesLecture notes in computer science, vol. 1484
dc.relation.publisherversionhttp://dx.doi.org/10.1007/3-540-49795-1_13
dc.rights© Springer
dc.rights.accessRightsopen access
dc.subject.otherMulti agent systems
dc.subject.otherMachine learning
dc.subject.otherDistributed artificial intelligence
dc.titleDistributed reinforcement learning in multi-agent decision systems
dc.typeconference paper*
dc.type.reviewPeerReviewed
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
distributed_giraldez_PAI_1998_ps.pdf
Size:
540.9 KB
Format:
Adobe Portable Document Format