Abstract
We consider a Markov decision process with a Borel state space, bounded rewards, and a bounded transition density satisfying a simultaneous Doeblin-Doob condition. An asymptotics for the discounted value function related to the existence of stationary strong 0-discount optimal policies is extended from the case of finite action sets to the case of compact action sets and continuous in action rewards and transition densities.
Similar content being viewed by others
References
Balder EI (1989) On compactness of the space of policies in stochastic dynamic programming. Stoch Proc Appl 32:141–150
Cavazos-Cadena R, Lasserre JB (1988) Strong 1-optimal stationary policies in denumerable Markov decision processes. Systems Control Letters 11:65–71
Doob JL (1953) Stochastic Processes. Wiley, New York
Himmelberg CJ, Parthasarathy T, VanVleck FS (1976) Optimal plans for dynamic programming models. Math Oper Res 1:390–394
Schäl M (1975) On dynamic programming: compactness of the space of policies. Stoch Proc Appl 3:345–354
Schäl M (1979) On dynamic programming and statistical decision theory. Ann Stat 7:432–445
Yushkevich AA (1994) Blackwell optimal policies in a Markov decision process with a Borel state space. ZOR 40:253–288
Yushkevich AA (1995) Strong 0-discount optimal policies in a Markov decision process with a Borel state space. ZOR 42:93–108
Yushkevich AA (1995a) Compactness of a measure space in dynamic programming revisited: an approach via extension theorem for Carathéodory functions. Technical report 95-2, Dept Math UNC-Charlotte
Yushkevich AA (1995b) Blackwell optimality in Borelian continuous in action Markov decision processes. Technical report 95-5, Dept Math UNC-Charlotte
Author information
Authors and Affiliations
Additional information
Supported by NSF grant DMS-9404177
Rights and permissions
About this article
Cite this article
Yushkevich, A.A. A note on asymptotics of discounted value function and strong 0-discount optimality. Mathematical Methods of Operations Research 44, 223–231 (1996). https://doi.org/10.1007/BF01194332
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01194332