Date: 2007
Type: Working Paper
Distribution-Free Learning
Working Paper, EUI ECO, 2007/01
SCHLAG, Karl H., Distribution-Free Learning, EUI ECO, 2007/01 - https://hdl.handle.net/1814/6689
Retrieved from Cadmus, EUI Research Repository
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
Cadmus permanent link: https://hdl.handle.net/1814/6689
ISSN: 1725-6704
Series/Number: EUI ECO; 2007/01
Publisher: European University Institute