Show simple item record

dc.contributor.authorFicici, Sevan
dc.contributor.authorParkes, David C.
dc.contributor.authorPfeffer, Avi J.
dc.date.accessioned2010-04-28T15:43:59Z
dc.date.issued2008
dc.identifier.citationFicici, Sevan, David C. Parkes, and Avi Pfeffer. 2008. Learning and solving many-player games through a cluster-based representation. In Uncertainty in artificial intelligence: Proceedings of the Twenty-fourth Conference: July 9-12, 2008, Helsinki, Finland, ed. D. McAllester, P. Myllymaki, 187-195. Corvallis, Or.: AUAI Press for Association for Uncertainty in Artificial Intelligence.en_US
dc.identifier.isbn0974903949en_US
dc.identifier.urihttp://nrs.harvard.edu/urn-3:HUL.InstRepos:4000306
dc.description.abstractIn addressing the challenge of exponential scaling with the number of agents we adopt a cluster-based representation to approximately solve asymmetric games of very many players. A cluster groups together agents with a similar “strategic view ” of the game. We learn the clustered approximation from data consisting of strategy profiles and payoffs, which may be obtained from observations of play or access to a simulator. Using our clustering we construct a reduced “twins” game in which each cluster is associated with two players of the reduced game. This allows our representation to be individuallyresponsive because we align the interests of every individual agent with the strategy of its cluster. Our approach provides agents with higher payoffs and lower regret on average than model-free methods as well as previous cluster-based methods, and requires only few observations for learning to be successful. The “twins ” approach is shown to be an important component of providing these low regret approximations.en_US
dc.description.sponsorshipEngineering and Applied Sciencesen_US
dc.language.isoen_USen_US
dc.publisherAssociation for Uncertainty in Artificial Intelligenceen_US
dc.relation.isversionofhttp://uai2008.cs.helsinki.fi/en_US
dc.relation.hasversionhttp://www.eecs.harvard.edu/econcs/pubs/ficici08.pdfen_US
dash.licenseLAA
dc.titleLearning and Solving Many-Player Games Through a Cluster-Based Representationen_US
dc.typeMonograph or Booken_US
dc.description.versionAccepted Manuscripten_US
dc.relation.journalThe Proc. 24th Conference in Uncertainty in Artificiall Intelligence (UAI'08)en_US
dash.depositing.authorParkes, David C.
dc.date.available2010-04-28T15:43:59Z
dash.contributor.affiliatedPfeffer, Avi
dash.contributor.affiliatedParkes, David


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record