Illustrated review of convergence conditions of the value iteration algorithm and the rolling horizon procedure for average-cost MDPs

Eugenio Vecchia (), Silvia Marco () and Alain Jean-Marie ()

Annals of Operations Research, 2012, vol. 199, issue 1, 193-214

Abstract: This paper is concerned with the links between the Value Iteration algorithm and the Rolling Horizon procedure, for solving problems of stochastic optimal control under the long-run average criterion, in Markov Decision Processes with finite state and action spaces. We review conditions of the literature which imply the geometric convergence of Value Iteration to the optimal value. Aperiodicity is an essential prerequisite for convergence. We prove that the convergence of Value Iteration generally implies that of Rolling Horizon. We also present a modified Rolling Horizon procedure that can be applied to models without analyzing periodicity, and discuss the impact of this transformation on convergence. We illustrate with numerous examples the different results. Finally, we discuss rules for stopping Value Iteration or finding the length of a Rolling Horizon. We provide an example which demonstrates the difficulty of the question, disproving in particular a conjectured rule proposed by Puterman. Copyright Springer Science+Business Media, LLC 2012

Keywords: Markov decision problems; Value iteration; Heuristic methods; Rolling horizon (search for similar items in EconPapers)
Date: 2012
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1007/s10479-012-1070-0 (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:annopr:v:199:y:2012:i:1:p:193-214:10.1007/s10479-012-1070-0

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10479

DOI: 10.1007/s10479-012-1070-0

Access Statistics for this article

Annals of Operations Research is currently edited by Endre Boros

More articles in Annals of Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().