Better-reply dynamics with bounded recall

Andriy Zapechelnyuk*

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    Abstract

    A decision maker is engaged in a repeated interaction with Nature. The objective of the decision maker is to guarantee to himself the average payoff as large as the best-reply payoff to Nature's empirical distribution of play, no matter what Nature does. The decision maker with perfect recall can achieve this objective by a simple better-reply strategy. In this paper we demonstrate that the relationship between perfect recall and bounded recall is not straightforward: The decision maker with bounded recall may fail to achieve this objective, no matter how long his recall and no matter what better-reply strategy he uses.

    Original languageEnglish
    Pages (from-to)869-879
    Number of pages11
    JournalMathematics of Operations Research
    Volume33
    Issue number4
    DOIs
    Publication statusPublished - Nov 2008

    Keywords

    • Approachability
    • Better-reply dynamics
    • Bounded recall
    • Fictitious play
    • Regret

    Fingerprint

    Dive into the research topics of 'Better-reply dynamics with bounded recall'. Together they form a unique fingerprint.

    Cite this