Sie können Bookmarks mittels Listen verwalten, loggen Sie sich dafür bitte in Ihr SLUB Benutzerkonto ein.
Medientyp:
E-Artikel
Titel:
A semimartingale characterization of average optimal stationary policies for Markov decision processes
Beteiligte:
Zhu, Quanxin;
Guo, Xianping
Erschienen:
Wiley, 2006
Erschienen in:
International Journal of Stochastic Analysis, 2006 (2006) 1
Sprache:
Englisch
DOI:
10.1155/jamsa/2006/81593
ISSN:
2090-3332;
2090-3340
Entstehung:
Anmerkungen:
Beschreibung:
This paper deals with discrete‐time Markov decision processes withBorel state and action spaces. The criterion to be minimized isthe average expected costs, and the costs may have neitherupper nor lower bounds. In our former paper (to appear in Journalof Applied Probability), weaker conditions are proposedto ensure the existence of average optimal stationary policies. Inthis paper, we further study some properties of optimal policies.Under these weaker conditions, we not only obtain twonecessary and sufficient conditions for optimal policies, but alsogive a “semimartingale characterization” of an average optimalstationary policy.