Accelerated modified policy iteration algorithms for Markov decision processes

Oleksandr Shlakhter () and Chi-Guhn Lee

Mathematical Methods of Operations Research, 2013, vol. 78, issue 1, 76 pages

Abstract: We propose a new approach to accelerate the convergence of the modified policy iteration method for Markov decision processes with the total expected discounted reward. In the new policy iteration an additional operator is applied to the iterate generated by Markov operator, resulting in a bigger improvement in each iteration. Copyright Springer-Verlag Berlin Heidelberg 2013

Keywords: Markov decision processes; Policy iteration; Modified policy iteration; Accelerated convergence (search for similar items in EconPapers)
Date: 2013
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1007/s00186-013-0432-y (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:78:y:2013:i:1:p:61-76

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

DOI: 10.1007/s00186-013-0432-y

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 ().