A note on the existence of optimal policies in total reward dynamic programs with compact action sets

A note on the existence of optimal policies in total reward dynamic programs with compact action sets

0.00 Avg rating0 Votes
Article ID: iaor20041188
Country: United States
Volume: 25
Issue: 4
Start Page Number: 657
End Page Number: 666
Publication Date: Nov 2000
Journal: Mathematics of Operations Research
Authors: , ,
Keywords: sets
Abstract:

This work deals with Markov decision processes (MDPs) with expected total rewards, discrete state spaces, and compact action sets. Within this framework, a question on the existence of optimal stationary policies, formulated by Puterman is considered. The paper concerns the possibility of obtaining an affirmative answer when additional assumptions are imposed on the decision model. Three conditions ensuring the existence of average optimal stationary policies in finite-state MDPs are analyzed, and it is shown that only the so-called structural continuity condition is a natural sufficient assumption under which the existence of total-reward optimal stationary policies can be guaranteed. In particular, this existence result holds for unichain MDPs with finite state space, but an example is provided to show that this general conclusion does not have an extension to the denumerable state space case.

Reviews

Required fields are marked *. Your email address will not be published.