Optimal mixing of Markov decision rules for MDP control

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

In this article we study Markov decision process (MDP) problems with the restriction that at decision epochs, only a finite number of given Markov decision rules are admissible. For example, the set of admissible Markov decision rules D could consist of some easy-implementable decision rules. Additionally, many open-loop control problems can be modeled as an MDP with such a restriction on the admissible decision rules. Within the class of available policies, optimal policies are generally nonstationary and it is difficult to prove that some policy is optimal. We give an example with two admissible decision rules - D={d
Original languageEnglish
Pages (from-to)307-342
JournalProbability in the Engineering and Informational Sciences
Volume25
Issue number3
DOIs
Publication statusPublished - 2011

Fingerprint

Dive into the research topics of 'Optimal mixing of Markov decision rules for MDP control'. Together they form a unique fingerprint.

Cite this