Article ID: | iaor19961759 |
Country: | Germany |
Volume: | 42 |
Issue: | 1 |
Start Page Number: | 93 |
End Page Number: | 108 |
Publication Date: | Jul 1995 |
Journal: | Mathematical Methods of Operations Research (Heidelberg) |
Authors: | Yushkevich A.A. |
The paper considers a Markov decision process with a Borel state space, a countable action space, finite action sets, bounded rewards and a bounded transition density satisfying a simultaneous Doeblin condition. The existence of stationary strong 0-discount optimal policies is proved.