×

zbMATH — the first resource for mathematics

Pointwise approximations of discounted Markov decision processes to optimal policies. (English) Zbl 1131.90068
Summary: This paper deals with discrete-time Markov decision processes with Borel state and control spaces, with possibly unbounded costs and compact control constraint sets, and the expected total discounted cost criterion. Conditions that allow to detect a value iteration policy which is a pointwise approximation to the optimal policy are given. Besides, two illustrative examples are supplied.

MSC:
90C40 Markov and semi-Markov decision processes
PDF BibTeX XML Cite