Optimality of Mixed Policies for Average Continuous-Time Markov Decision Processes with Constraints

Optimality of Mixed Policies for Average Continuous-Time Markov Decision Processes with Constraints

0.00 Avg rating0 Votes
Article ID: iaor20164232
Volume: 41
Issue: 4
Start Page Number: 1276
End Page Number: 1296
Publication Date: Nov 2016
Journal: Mathematics of Operations Research
Authors: ,
Keywords: programming: markov decision
Abstract:

This article concerns the average criteria for continuous‐time Markov decision processes with N constraints. We show the following; (a) every extreme point of the space of performance vectors corresponding to the set of stable measures is generated by a deterministic stationary policy; and (b) there exists a mixed optimal policy, where the mixture is over no more than N + 1 deterministic stationary policies.

Reviews

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 Your email address will not be published.