Partially Observable Risk-Sensitive Markov Decision Processes
Preprint
Abstract
We consider the problem of minimizing a certainty equivalent of the total or discounted cost over a finite and an infinite time horizon which is generated by a Partially Observable Markov Decision Process (POMDP). The certainty equivalent is defined by $U^{-1}(EU(Y))$ where $U$ is an increasing function. In contrast to a risk-neutral decision maker this optimization criterion takes the variability of the cost into account. It contains as a special case the classical risk-sensitive optimization criterion with an exponential utility. We show that this optimization problem can be solved by embedding the problem into a completely observable Markov Decision Process with extended state space and give conditions under which an optimal policy exists. The state space has to be extended by the joint conditional distribution of current unobserved state and accumulated cost. In case of an exponential utility, the problem simplifies considerably and we rediscover what in previous literature has been named information state. However, since we do not use any change of measure techniques here, our approach is simpler. A small numerical example, namely the classical repeated casino game with unknown success probability is considered to illustrate the influence of the certainty equivalent and its parameters.
Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Risk-sensitive dividend problemsEuropean Journal of Operational Research, 2015
- Markov Decision Processes with Applications to Finance2011
- Successive approximations in partially observable controlled Markov chains with risk-sensitive average criterionStochastics, 2005
- Risk-Sensitive Portfolio Optimization With Completely and Partially Observed FactorsIEEE Transactions on Automatic Control, 2004
- Economic Properties of the Risk Sensitive Criterion for Portfolio ManagementReview of Accounting and Finance, 2003
- Partially Observed Control Problems with Multiplicative Cost1999
- Risk-sensitive control and dynamic games for partially observed discrete-time nonlinear systemsIEEE Transactions on Automatic Control, 1994
- Stochastic Control of Partially Observable Systems1992
- Foundations of Non-stationary Dynamic Programming with Discrete Time Parameter1970
- Optimal control of partially observable Markovian systemsJournal of the Franklin Institute, 1965