Article ID: | iaor19972491 |
Country: | Germany |
Volume: | 44 |
Issue: | 2 |
Start Page Number: | 205 |
End Page Number: | 221 |
Publication Date: | Sep 1996 |
Journal: | Mathematical Methods of Operations Research (Heidelberg) |
Authors: | Feinberg E.A., Sonin I.M. |
Keywords: | programming: dynamic |
The authors construct examples of Markov Decision Processes for which, for a given initial state and for a given nonstationary transient policy, there is no equivalent (randomized) stationary policy, i.e. there is no stationary policy which occupation measure is equal to the occupation measure of a given policy. They also investigate the relation between the existence of equivalent stationary policies in special models and the existence of equivalent strategies in various classes of nonstationary policies in general models.