Approximations in Bayesian controlled Markov chains

K.M. Hee, van

    Onderzoeksoutput: Boek/rapportRapportAcademic

    22 Downloads (Pure)


    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.
    Originele taal-2Engels
    Plaats van productieEindhoven
    UitgeverijTechnische Hogeschool Eindhoven
    Aantal pagina's11
    StatusGepubliceerd - 1976

    Publicatie series

    NaamMemorandum COSOR
    ISSN van geprinte versie0926-4493


    Duik in de onderzoeksthema's van 'Approximations in Bayesian controlled Markov chains'. Samen vormen ze een unieke vingerafdruk.

    Citeer dit