Ergodic control of partially observed Markov chains

Borkar, Vivek S (1998) Ergodic control of partially observed Markov chains. In: Systems & Control Letters, 34 (4). pp. 185-189.

PDF art.pdf - Published Version Restricted to Registered users only Download (95Kb) | Request a copy

Abstract

The ergodic or long-run average cost control problem for a partially observed finite-state Markov chain is studied via the associated fully observed separated control problem for the nonlinear filter. Dynamic programming equations for the latter are derived, leading to existence and characterization of optimal stationary policies.

Item Type:	Journal Article
Additional Information:	Copyright of this article belongs to Elsevier Science.
Keywords:	Controlled Markov chains;Ergodic control;Partial observations;Dynamic programming;Optimal stationary policies
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation (Formerly, School of Automation)
Date Deposited:	17 Jul 2009 07:49
Last Modified:	19 Sep 2010 05:27
URI:	http://eprints.iisc.ernet.in/id/eprint/19282

Actions (login required)

View Item