Risk-Sensitive and Mean Variance Optimality in Markov Decision Processes
In this paper we consider unichain Markov decision processes with finite state space and compact actions spaces where the stream of rewards generated by the Markov processes is evaluated by an exponential utility function with a given risk sensitivity coefficient (so-called risk-sensitive models). If the risk sensitivity coefficient equals zero (risk-neutral case) we arrive at a standard Markov decision process. Then we can easily obtain necessary and sufficient mean reward optimality conditions and the variability can be evaluated by the mean variance of total expected rewards. For the risk-sensitive case we establish necessary and sufficient optimality conditions for maximal (or minimal) growth rate of expectation of the exponential utility function, along with mean value of the corresponding certainty equivalent, that take into account not only the expected values of the total reward but also its higher moments.
Volume (Year): 7 (2013)
Issue (Month): 3 (November)
|Contact details of provider:|| Postal: Opletalova 26, CZ-110 00 Prague|
Phone: +420 2 222112330
Fax: +420 2 22112304
Web page: http://ies.fsv.cuni.cz/
More information through EDIRC
|Order Information:|| Web: http://auco.cuni.cz/ Email: |
References listed on IDEAS
Please report citation or reference errors to , or , if you are the registered author of the cited work, log in to your RePEc Author Service profile, click on "citations" and make appropriate adjustments.:
- Stratton C. Jaquette, 1976. "A Utility Criterion for Markov Decision Processes," Management Science, INFORMS, vol. 23(1), pages 43-49, September.
- Kawai, Hajime, 1987. "A variance minimization problem for a Markov decision process," European Journal of Operational Research, Elsevier, vol. 31(1), pages 140-145, July.
- Harry Markowitz, 1952. "Portfolio Selection," Journal of Finance, American Finance Association, vol. 7(1), pages 77-91, 03.
- Ronald A. Howard & James E. Matheson, 1972. "Risk-Sensitive Markov Decision Processes," Management Science, INFORMS, vol. 18(7), pages 356-369, March.
When requesting a correction, please mention this item's handle: RePEc:fau:aucocz:au2013_146. See general information about how to correct material in RePEc.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Lenka Stastna)
If references are entirely missing, you can add them using this form.