Markov strategies in dynamic programming

K.M. Hee, van

    Research output: Book/ReportReportAcademic

    51 Downloads (Pure)

    Abstract

    It will be proven that the supremum of the expected total return over the Markov strategies equals the supremum over all strategies. The model assumptions are: the state space is countable, the action space is measurable and the supremum of the expected total of the positive rewards over the Markov strategies is finite.
    Original languageEnglish
    Place of PublicationEindhoven
    PublisherTechnische Hogeschool Eindhoven
    Number of pages9
    Publication statusPublished - 1975

    Publication series

    NameMemorandum COSOR
    Volume7520
    ISSN (Print)0926-4493

    Fingerprint

    Dive into the research topics of 'Markov strategies in dynamic programming'. Together they form a unique fingerprint.

    Cite this