Adaptive control of average Markov decision chains under the Lyapunov stability condition

Rolando Cavazos-Cadena

Mathematical Methods of Operations Research, 2001, vol. 54, issue 1, 63-99

Abstract: This note concerns discrete-time Markov decision processes with denumerable state space. A control policy is graded by the long-run expected average reward criterion, and the main feature of the model is that the reward function and the transition law depend on an unknown parameter. Besides standard continuity-compactness restrictions, it is supposed that the controller can use the observed history to generate a consistent estimation scheme, and that the system's transition-reward structure satisfies an adaptive version of the Lyapunov function condition. Within this context, a special implementation of the non stationary value iteration method is studied, and it is shown that this technique produces convergent approximations to the solution of the optimality equation, result that is used to build an optimal adaptive policy. Copyright Springer-Verlag Berlin Heidelberg 2001

Keywords: Key words: Schweitzer's Transformation; Pause Control; Non stationary value iteration; Consistent estimation; Adaptive optimal policy; Discrepancy function.; AMS Classification: 90C40; 93E20. (search for similar items in EconPapers)
Date: 2001
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1007/s001860100138 (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:54:y:2001:i:1:p:63-99

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

DOI: 10.1007/s001860100138

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 ().