Risk-sensitive optimal control for Markov decision processes with monotone cost

Borkar, VS and Meyn, SP (2002) Risk-sensitive optimal control for Markov decision processes with monotone cost. In: Mathematics of Operations Research, 27 (1). pp. 192-209.

PDF RISK-SENSITIVE.pdf - Published Version Restricted to Registered users only Download (516kB) | Request a copy

Abstract

The existence of an optimal feedback law is established for the risk-sensitive optimal control problem with denumerable state space. The main assumptions imposed are irreducibility and a near monotonicity condition on the one-step cost function. A solution can be found constructively using either value iteration or policy iteration under suitable conditions on initial feedback law.

Item Type:	Journal Article
Publication:	Mathematics of Operations Research
Publisher:	INFORMS
Additional Information:	Copyright of this article belongs to INFORMS.
Keywords:	Optimal control;risk-sensitive control;dynamic programming
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	28 Jul 2011 08:04
Last Modified:	11 Oct 2018 18:23
URI:	http://eprints.iisc.ac.in/id/eprint/39383

Actions (login required)

View Item