A Wide Range No-Regret Theorem

Ehud Lehrer () and Dinah Rosenberg
Additional contact information
Dinah Rosenberg: U. Paris Nord

Game Theory and Information from EconWPA

Abstract: In a sequential decision problem at any stage a decision maker, based on the history, takes a decision and receives a payoff which depends also on the realized state of nature. A strategy, f, is said to be as good as an alternative strategy g at a sequence of states, if in the long run f does, on average, at least as well as g does. It is shown that for any distribution, P, over the alternative strategies there is a strategy f which is, at any sequence of states, as good as P-almost any alternative g.

Keywords: No-regret; Approachability; large spaces (search for similar items in EconPapers)
JEL-codes: C7 D8 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-mic
Date: 2003-12-11
Note: Type of Document - pdf
View list of references

Downloads: (external link)
http://129.3.20.41/eps/game/papers/0312/0312004.pdf (application/pdf)

Related works:
Journal Article: A wide range no-regret theorem (2003)
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: http://EconPapers.repec.org/RePEc:wpa:wuwpga:0312004

Access Statistics for this paper

More papers in Game Theory and Information from EconWPA
Series data maintained by EconWPA ().