Show simple item record

dc.contributor.authorSCHLAG, Karl H.
dc.date.accessioned2007-02-07T16:36:06Z
dc.date.available2007-02-07T16:36:06Z
dc.date.issued2007
dc.identifier.issn1725-6704
dc.identifier.urihttps://hdl.handle.net/1814/6689
dc.description.abstractWe select among rules for learning which of two actions in a stationary decision problem achieves a higher expected payoffs when payoffs realized by both actions are known in previous instances. Only a bounded set containing all possible payoffs is known. Rules are evaluated using maximum risk with maximin utility, minimax regret, com- petitive ratio and selection procedures being special cases. A randomized variant of …fictitious play attains minimax risk for all risk functions with ex-ante expected payoffs increasing in the number of observations. Fictitious play itself has neither of these two properties. Tight bounds on maximal regret and probability of selecting the best action are includeden
dc.format.extent416356 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherEuropean University Institute
dc.relation.ispartofseriesEUI ECOen
dc.relation.ispartofseries2007/01en
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectFictitious playen
dc.subjectnonparametricen
dc.subjectfinite sampleen
dc.subjectmatched pairsen
dc.subjectforegone payoffsen
dc.subjectminimax risken
dc.subjectex-ante improvingen
dc.subjectselection procedureen
dc.subjectD83en
dc.subjectD81en
dc.subjectC44en
dc.titleDistribution-Free Learningen
dc.typeWorking Paperen
dc.neeo.contributorSCHLAG|Karl H.|aut|
eui.subscribe.skiptrue


Files associated with this item

Icon

This item appears in the following Collection(s)

Show simple item record