Value iteration and approximately optimal stationary policies in finite-state average Markov decision chains

Rolando Cavazos-Cadena and Rolando Cavazos-Cadena

Mathematical Methods of Operations Research, 2002, vol. 56, issue 2, 196 pages

Abstract: This work concerns finte-state Markov decision chains endowed with the long-run average reward criterion. Assuming that the optimality equation has a solution, it is shown that a nearly optimal stationary policy, as well as an approximation to the optimal average reward within a specified error, can be obtained in a finite number of steps of the value iteration method. These results extend others already available in the literature, which were established under more stringent restrictions on the ergodic structure of the decision process. Copyright Springer-Verlag Berlin Heidelberg 2002

Keywords: AMS Subject Classifications. Primary, 90C40, 93E20; Secondary, 60J05, Key words: Successive approximations, Markov decision processes, Schweitzer's Transformation, Optimality Equation, Convergence of the value iteration approximations, (search for similar items in EconPapers)
Date: 2002
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://hdl.handle.net/10.1007/s001860200205 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:mathme:v:56:y:2002:i:2:p:181-196

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/00186

DOI: 10.1007/s001860200205

Access Statistics for this article

Mathematical Methods of Operations Research is currently edited by Oliver Stein

More articles in Mathematical Methods of Operations Research from Springer, Gesellschaft für Operations Research (GOR), Nederlands Genootschap voor Besliskunde (NGB)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().