Approximations in Bayesian controlled Markov chains

K.M. Hee, van

    Research output: Book/ReportReportAcademic

    21 Downloads (Pure)

    Abstract

    A class of Markov decision processes is considered with a finite state and action space and with an incompletely known transition mechanism. The controller is looking for a strategy maximizing the Bayesian expected total discounted return. In section 2 approximations are given for this value and in section 3 we indicate how to compute the value for a fixed prior distribution.
    Original languageEnglish
    Place of PublicationEindhoven
    PublisherTechnische Hogeschool Eindhoven
    Number of pages11
    Publication statusPublished - 1976

    Publication series

    NameMemorandum COSOR
    Volume7615
    ISSN (Print)0926-4493

    Fingerprint

    Dive into the research topics of 'Approximations in Bayesian controlled Markov chains'. Together they form a unique fingerprint.

    Cite this