On uniformly nearly-optimal Markov strategies

J. Wal, van der

Research output: Book/ReportReportAcademic

23 Downloads (Pure)

Abstract

In this paper the following result is proved. In any total reward countable state Markov decision process a Markov strategy p exists which is uniformly nearly-optimal in the following sense: v(p) = v* - e (e+u*) . Here v* denotes the value function of the process, u* denotes the value of the process if all negative rewards are neglected, and e is the unit function.
Original languageEnglish
Place of PublicationEindhoven
PublisherTechnische Hogeschool Eindhoven
Number of pages14
Publication statusPublished - 1981

Publication series

NameMemorandum COSOR
Volume8116
ISSN (Print)0926-4493

Fingerprint Dive into the research topics of 'On uniformly nearly-optimal Markov strategies'. Together they form a unique fingerprint.

Cite this