Risk-sensitive optimal control of hidden Markov models: structural results

Author

Fernandez-Gaucherand, E. ; Marcus, Steven I.

Author_Institution

Dept. of Syst. & Ind. Eng., Arizona Univ., Tucson, AZ

Volume

42

Issue

10

fYear

1997

fDate

10/1/1997 12:00:00 AM

Firstpage

1418

Lastpage

1422

Abstract

The authors consider a risk-sensitive optimal control problem for (finite state and action spaces) hidden Markov models (HMM). They present results of an investigation on the nature and structure of risk-sensitive controllers for HMM. Several general structural results are presented, as well as a particular case study of a popular benchmark problem. For the latter, they obtain structural results for the optimal risk-sensitive controller and compare it to that of the risk-neutral controller. Furthermore, they show that indeed the risk-sensitive controller and its corresponding information state converge to the known solutions for the risk-neutral situation as the risk factor goes to zero. They also study the infinite and general risk aversion cases

Keywords

hidden Markov models; optimal control; stochastic systems; HMM; finite action space; finite state space; hidden Markov models; risk-neutral controller; risk-sensitive optimal control; structural results; Additives; Automatic control; Cost function; Delta modulation; Equations; Hidden Markov models; Optimal control; Probability; Statistics; Stochastic processes;

fLanguage

English

Journal_Title

Automatic Control, IEEE Transactions on

Publisher

ieee

ISSN

0018-9286

Type

jour

DOI

10.1109/9.633830

Filename

633830