Alexey Piunovskiy, Yi Zhang. Discounted Continuous-time Markov Decision Processes with Unbounded Rates: the Dynamic Programming Approach
Submitted on: Dec 03, 2012, 06:24:03
Natural Sciences / Mathematics / Algebra
Description: This paper deals with unconstrained discounted continuous-time Markov decision processes in Borel state and action spaces. Under some conditions imposed on the primitives, allowing unbounded transition rates and unbounded (from both above and below) cost rates, we show the regularity of the controlled process, which ensures the underlying models to be well defined. Then we develop the dynamic programming approach by showing that the Bellman equation is satisfied (by the optimal value). Finally, under some compactness-continuity conditions, we obtain the existence of a deterministic stationary optimal policy out of the class of randomized history-dependent policies.
The Library of Congress (USA) reference page : http://lccn.loc.gov/cn2013300046.
The Library and Archives Canada reference page: http://collectionscanada.gc.ca/ourl/res.php?url_ver=Z39.88......
To read the article posted on Intellectual Archive web site please click the link below.