On the Milito-Cruz adaptive control scheme for Markov chains

Borkar, VS (1993) On the Milito-Cruz adaptive control scheme for Markov chains. In: Journal of Optimization Theory and Applications, 77 (2). pp. 387-397.

PDF Milito.pdf - Published Version Restricted to Registered users only Download (550kB) | Request a copy

Abstract

Milito and Cruz have introduced a novel adaptive control scheme for finite Markov chains when a finite parametrized family of possible transition matrices is available. The scheme involves the minimization of a composite functional of the observed history of the process incorporating both control and estimation aspects. We prove the a.s. optimality of a similar scheme when the state space is countable and the parameter space a compact subset ofR.

Item Type:	Journal Article
Publication:	Journal of Optimization Theory and Applications
Publisher:	Springer
Additional Information:	Copyright of this article belongs to Springer.
Keywords:	Controlled Markov chains;adaptive control;cost-biased estimation;asymptotic optimality;ergodic control
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	18 Feb 2011 07:45
Last Modified:	18 Feb 2011 07:45
URI:	http://eprints.iisc.ac.in/id/eprint/35649

Actions (login required)

View Item