Distribution-Free Learning

DSpace/Manakin Repository

Show simple item record

dc.contributor.author SCHLAG, Karl H.
dc.date.accessioned 2007-02-07T16:36:06Z
dc.date.available 2007-02-07T16:36:06Z
dc.date.issued 2007
dc.identifier.issn 1725-6704
dc.identifier.uri http://hdl.handle.net/1814/6689
dc.description.abstract We 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 included en
dc.format.extent 416356 bytes
dc.format.mimetype application/pdf
dc.language.iso en en
dc.publisher European University Institute
dc.relation.ispartofseries EUI ECO en
dc.relation.ispartofseries 2007/01 en
dc.subject Fictitious play en
dc.subject nonparametric en
dc.subject finite sample en
dc.subject matched pairs en
dc.subject foregone payoffs en
dc.subject minimax risk en
dc.subject ex-ante improving en
dc.subject selection procedure en
dc.subject D83 en
dc.subject D81 en
dc.subject C44 en
dc.title Distribution-Free Learning en
dc.type Working Paper en
dc.neeo.contributor SCHLAG|Karl H.|aut|
eui.subscribe.skip true


Files in this item

This item appears in the following Collection(s)

Show simple item record