Markov programming by successive approximations with respect to weighted supremum norms

J. Wessels

Research output: Book/ReportReportAcademic

81 Downloads (Pure)

Abstract

Markovian decision processes are considered in the situation of discrete time. countable state space. and general decision space. By introducing a Banach space with a weighted supremum norm, conditions are derived, which guarantee convergence of successive approximations to the value function. These conditions are weaker then those required by the usual supnorm approach. Several properties of the successive approximations are derived.
Original languageEnglish
Place of PublicationEindhoven
PublisherTechnische Hogeschool Eindhoven
Number of pages12
Publication statusPublished - 1974

Publication series

NameMemorandum COSOR
Volume7413
ISSN (Print)0926-4493

Fingerprint Dive into the research topics of 'Markov programming by successive approximations with respect to weighted supremum norms'. Together they form a unique fingerprint.

  • Cite this

    Wessels, J. (1974). Markov programming by successive approximations with respect to weighted supremum norms. (Memorandum COSOR; Vol. 7413). Technische Hogeschool Eindhoven.