Non-randomized policies for constrained Markov decision processes
Original Article
First Online:
Received:
Accepted:
- 89 Downloads
- 13 Citations
Abstract
This paper addresses constrained Markov decision processes, with expected discounted total cost criteria, which are controlled by non-randomized policies. A dynamic programming approach is used to construct optimal policies. The convergence of the series of finite horizon value functions to the infinite horizon value function is also shown. A simple example illustrating an application is presented.
Keywords
Constrained Markov Decision processes Dynamic programming Non-randomized policiesPreview
Unable to display preview. Download preview PDF.
References
- Altman E, Shwartz A (1991) Sensitivity of constrained Markov decision processes. Ann Oper Res 32:1–22MATHCrossRefGoogle Scholar
- Chen RC (2004) Constrained stochastic control and optimal search. In: Proceedings of the 43rd IEEE conference on decision and control, Bahamas, vol 3, pp 3013-3020, 14–173Google Scholar
- Chen RC (2005) Constrained Markov processes and optimal truncated sequential detection. In: Defence applications of signal processing proceedings, Utah, pp 28–31Google Scholar
- Chen RC, Blankenship GL (2002) Dynamic programming equations for constrained stochastic control. In: Proceedings of the 2002 American control conference, Anchorage, AK, vol 3, pp 2014–2022, 8–10Google Scholar
- Chen RC, Blankenship GL (2004) Dynamic programming equations for discounted constrained stochastic control. IEEE Trans. Autom. Control 49(5):699–709CrossRefGoogle Scholar
- Coraluppi S, Marcus SI (2000) Mixed risk-neutral/minimax control of discrete-time, finite-state Markov decision processes. IEEE Trans Autom Control 45(3):528–532MATHCrossRefGoogle Scholar
- Piunovskiy AB, Mao X (2000) Constrained Markovian decision processes: the dynamic programming approach. Oper Res Lett 27:119–126MATHCrossRefGoogle Scholar
- Rockafellar RT, Wets RJ-B (1998) Variational analysis. Springer, Berlin Heidelberg New YorkMATHGoogle Scholar
Copyright information
© Springer-Verlag 2007