The generation of successive approximation methods for Markov decision processes by using stopping times

J.A.E.E. van Nunen, J. Wessels

    Research output: Book/ReportReportAcademic

    48 Downloads (Pure)

    Abstract

    In this paper we will consider several variants of the standard successive approximation technique for Markov decision processes. It will be shown how these variants can be generated by stopping times. Furthermore it will be demonstrated how this class of techniques can be extended to a class of value oriented techniques. This latter class contains as extreme elements several variants of Howard's policy iteration method. For all methods presented extrapolations are given in the form of MacQueen's upper and lower bounds.
    Original languageEnglish
    Place of PublicationEindhoven
    PublisherTechnische Hogeschool Eindhoven
    Number of pages13
    Publication statusPublished - 1976

    Publication series

    NameMemorandum COSOR
    Volume7622
    ISSN (Print)0926-4493

    Fingerprint Dive into the research topics of 'The generation of successive approximation methods for Markov decision processes by using stopping times'. Together they form a unique fingerprint.

    Cite this