Continuous-Time Markov Decision Processes with Exponential Utility

Zhang, Y ORCID: 0000-0002-3200-6306 (2017) Continuous-Time Markov Decision Processes with Exponential Utility. SIAM JOURNAL ON CONTROL AND OPTIMIZATION, 55 (4). pp. 2636-2660.

Text YiZhang2016SICONRevRoundTwo.pdf - Author Accepted Manuscript Download (359kB)

Abstract

In this paper, we consider a continuous-time Markov decision process (CTMDP) in Borel spaces, where the certainty equivalent with respect to the exponential utility of the total undiscounted cost is to be minimized. The cost rate is nonnegative. We establish the optimality equation. Under the compactness-continuity condition, we show the existence of a deterministic stationary optimal policy. We reduce the risk-sensitive CTMDP problem to an equivalent risk-sensitive discrete-time Markov decision process, which is with the same state and action spaces as the original CTMDP. In particular, the value iteration algorithm for the CTMDP problem follows from this reduction. We essentially do not need to impose a condition on the growth of the transition and cost rate in the state, and the controlled process could be explosive.

Item Type:	Article
Uncontrolled Keywords:	continuous-time Markov decision processes, exponential utility, total undiscounted criteria, risk-sensitive criterion, optimality equation
Depositing User:	Symplectic Admin
Date Deposited:	20 Nov 2017 11:33
Last Modified:	19 Jan 2023 06:50
DOI:	10.1137/16M1086261
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3012367