Maximum Entropy Correlated Equilibria

dc.contributor.advisor	Leslie Kaelbling
dc.contributor.author	Ortiz, Luis E.
dc.contributor.author	Schapire, Robert E.
dc.contributor.author	Kakade, Sham M.
dc.contributor.other	Learning and Intelligent Systems
dc.date.accessioned	2006-03-20T19:24:59Z
dc.date.available	2006-03-20T19:24:59Z
dc.date.issued	2006-03-20
dc.identifier.other	MIT-CSAIL-TR-2006-021
dc.identifier.uri	http://hdl.handle.net/1721.1/31339
dc.description.abstract	We study maximum entropy correlated equilibria in (multi-player)games and provide two gradient-based algorithms that are guaranteedto converge to such equilibria. Although we do not provideconvergence rates for these algorithms, they do have strong connectionsto other algorithms (such as iterative scaling) which are effectiveheuristics for tasks such as statistical estimation.
dc.format.extent	15 p.
dc.format.extent	301190 bytes
dc.format.extent	876790 bytes
dc.format.mimetype	application/pdf
dc.format.mimetype	application/postscript
dc.language.iso	en_US
dc.relation.ispartofseries	Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory
dc.subject	Game Theory, Graphical Games, Graphical Models, Normal-form Games, Optimization
dc.title	Maximum Entropy Correlated Equilibria