Borkar, V. S. ; Mundra, S. M. (1999) Bayesian parameter estimation and adaptive control of Markov processes with time-averaged cost Applicationes Mathematicae, 25 (4). pp. 339-358. ISSN 1233-7234
Full text not available from this repository.
Official URL: http://matwbn.icm.edu.pl/ksiazki/zm/zm25/zm2538.pd...
Abstract
This paper considers Bayesian parameter estimation and an associated adaptive control scheme for controlled Markov chains and diffu- sions with time-averaged cost. Asymptotic behaviour of the posterior law of the parameter given the observed trajectory is analyzed. This analysis sug- gests a "cost-biased" estimation scheme and associated self-tuning adaptive control. This is shown to be asymptotically optimal in the almost sure sense.
| Item Type: | Article |
|---|---|
| Source: | Copyright of this article belongs to Institute of Mathematics of the Polish Academy of Sciences. |
| Keywords: | Bayesian Estimation; Cost-biased Estimate; Adaptive Control; Time-averaged Cost; Asymptotic Optimality |
| ID Code: | 81441 |
| Deposited On: | 06 Feb 2012 05:02 |
| Last Modified: | 06 Feb 2012 05:02 |
Repository Staff Only: item control page
