A wide range no-regret theorem

Ehud Lehrer*

*Corresponding author for this work

Research output: Contribution to journalReview articlepeer-review

43 Scopus citations

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, μ, over the alternative strategies there is a strategy f which is, at any sequence of states, as good as μ-almost any alternative g.

Original languageEnglish
Pages (from-to)101-115
Number of pages15
JournalGames and Economic Behavior
Volume42
Issue number1
DOIs
StatePublished - Jan 2003

Funding

FundersFunder number
Israel Science Foundation178/9910.0

    Keywords

    • Approachability
    • Regret-free strategy
    • Replacing scheme
    • Sequential decision problem

    Fingerprint

    Dive into the research topics of 'A wide range no-regret theorem'. Together they form a unique fingerprint.

    Cite this