Abstract
Some finite horizon MDPs and infinite horizon discounted MDPs with constraints are discussed in this paper. Some available algorithms are given separately for various models discussed in this paper.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Frederick, J. Beutler and Keith, W. Ross, Optimal Policies for Controlled Markov Chains with a Constraint,J. Math. Anal. Appl.,112 (1985), 236–252.
Furukawa, N., Characterization of Optimal Policies in Vector-valued Markovian Decision Processes,Math. Oper. Res.,5:2 (1980), 271–279.
Furukawa, N., Vector-valued Markovian Decision Processes with Countable State Space, Recent Developments in Markov Decision Processes, Academic Press, London, New York, Toronto, Sydney, San Francisco, 1980, 205–223.
Derman, C., Finite State Markovian Decision Processes, Academic Press, New York, 1970.
Author information
Authors and Affiliations
Additional information
This project is supported by the National Natural Science Foundation of China.
Rights and permissions
About this article
Cite this article
Liu, J., Liu, K. Markov decision programming with constraints. Acta Mathematicae Applicatae Sinica 10, 1–11 (1994). https://doi.org/10.1007/BF02006255
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02006255