Markov decision processes with unbounded rewards

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

    Onderzoeksoutput: Boek/rapportRapportAcademic

    28 Downloads (Pure)


    Markov decision processes which allow for an unbounded reward structure are considered. Conditions are given which allow successive approximations with a convergence in some strong sense. This "strong" convergence enables the construction of upper and lower bounds. The conditions are weaker than those proposed by Lippman [15], Harrison [5] and Wessels [28] and are in fact a slight generalization of the conditions proposed by Van Nunen [21]. A successive approximation algorithm will be indicated. The conditions will be analysed and compared with those in literature.
    Originele taal-2Engels
    Plaats van productieEindhoven
    UitgeverijTechnische Hogeschool Eindhoven
    Aantal pagina's24
    StatusGepubliceerd - 1976

    Publicatie series

    NaamMemorandum COSOR
    ISSN van geprinte versie0926-4493

    Vingerafdruk Duik in de onderzoeksthema's van 'Markov decision processes with unbounded rewards'. Samen vormen ze een unieke vingerafdruk.

    Citeer dit