Distribution-Free Learning

Karl Schlag

No ECO2007/01, Economics Working Papers from European University Institute

Abstract: We select among rules for learning which of two actions in a stationary decision problem achieves a higher expected payo¤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, competitive 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.

Keywords: fictitious play; nonparametric; finite sample; matched pairs; foregone payoffs; minimax risk; ex-ante improving; selection procedure (search for similar items in EconPapers)
JEL-codes: C44 D81 D83 (search for similar items in EconPapers)
Date: 2007
New Economics Papers: this item is included in nep-cba and nep-cbe
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://cadmus.iue.it/dspace/bitstream/1814/6689/3/ECO-2007-01.pdf main text
Our link check indicates that this URL is bad, the error code is: 404 Not Found

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eui:euiwps:eco2007/01

Access Statistics for this paper

More papers in Economics Working Papers from European University Institute Badia Fiesolana, Via dei Roccettini, 9, 50014 San Domenico di Fiesole (FI) Italy. Contact information at EDIRC.
Bibliographic data for series maintained by Cécile Brière ().