Show simple item record

dc.contributor.authorOliehoek, Frans A.
dc.contributor.authorWitwicki, Stefan J.
dc.contributor.authorKaelbling, Leslie P.
dc.date.accessioned2014-05-19T18:27:09Z
dc.date.available2014-05-19T18:27:09Z
dc.date.issued2012-07
dc.identifier.urihttp://hdl.handle.net/1721.1/87052
dc.description.abstractThis paper presents a theoretical advance by which factored POSGs can be decomposed into local models. We formalize the interface between such local models as the influence agents can exert on one another; and we prove that this interface is sufficient for decoupling them. The resulting influence-based abstraction substantially generalizes previous work on exploiting weakly-coupled agent interaction structures. Therein lie several important contributions. First, our general formulation sheds new light on the theoretical relationships among previous approaches, and promotes future empirical comparisons that could come by extending them beyond the more specific problem contexts for which they were developed. More importantly, the influence-based approaches that we generalize have shown promising improvements in the scalability of planning for more restrictive models. Thus, our theoretical result here serves as the foundation for practical algorithms that we anticipate will bring similar improvements to more general planning contexts, and also into other domains such as approximate planning, decision-making in adversarial domains, and online learning.en_US
dc.description.sponsorshipUnited States. Air Force Office of Scientific Research. Multidisciplinary University Research Initiative (Project FA9550-09-1-0538)en_US
dc.language.isoen_US
dc.publisherAssociation for the Advancement of Artifical Intelligenceen_US
dc.relation.isversionofhttp://www.aaai.org/Conferences/AAAI/2012/aaai12program.pdfen_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alikeen_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/4.0/en_US
dc.sourceMIT web domainen_US
dc.titleInfluence-Based Abstraction for Multiagent Systemsen_US
dc.typeArticleen_US
dc.identifier.citationOliehoek, Frans A, Stefan J. Witwicki, and Leslie P. Kaelbling. "Influence-Based Abstraction for Multiagent Systems." Proceedings of the 26th AAAI Conference on Artificial Intelligence, July 22-26, 2012, Toronto, Ontario, Canada.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.mitauthorOliehoek, Frans A.en_US
dc.contributor.mitauthorKaelbling, Leslie P.en_US
dc.relation.journalProceedings of the 26th AAAI Conference on Artificial Intelligenceen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dspace.orderedauthorsOliehoek, Frans A.; Witwicki, Stefan J.; Kaelbling, Leslie P.en_US
dc.identifier.orcidhttps://orcid.org/0000-0001-6054-7145
mit.licenseOPEN_ACCESS_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record