Conditions for the uniqueness of optimal policies of discounted Markov decision processes

ISSN： 1432-2994

Source： Mathematical Methods of Operations Research, Vol.60, Iss.3, 2004-12, pp. : 415-436

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

Related content

An envelope theorem and some applications to discounted Markov decision processes

By Cruz-Suárez Hugo

Mathematical Methods of Operations Research, Vol. 67, Iss. 2, 2008-04 ,pp. : 299-321

Springer Publishing Company

Access to resources Recommend Favorite

Non-randomized policies for constrained Markov decision processes

By Chen Richard Feinberg Eugene

Mathematical Methods of Operations Research, Vol. 66, Iss. 1, 2007-08 ,pp. : 165-179

Springer Publishing Company

Access to resources Recommend Favorite

Ranking policies in discrete Markov decision processes

By Dai Peng

Annals of Mathematics and Artificial Intelligence, Vol. 59, Iss. 1, 2010-05 ,pp. : 107-123

Springer Publishing Company

Access to resources Recommend Favorite

Markov control processes with randomized discounted cost

By González-Hernández Juan

Mathematical Methods of Operations Research, Vol. 65, Iss. 1, 2007-02 ,pp. : 27-44

Springer Publishing Company

Access to resources Recommend Favorite

Optimal threshold probability in undiscounted Markov decision processes with a target set

By Ohtsubo Y.

Applied Mathematics and Computation, Vol. 149, Iss. 2, 2004-02 ,pp. : 519-532

Elsevier

Access to resources Recommend Favorite