Article ID Journal Published Year Pages File Type
753325 Systems & Control Letters 2006 7 Pages PDF
Abstract

Stochastic approximation algorithms with additional noise that can be modelled as a controlled Markov process are analyzed and shown to track the solutions of a differential inclusion defined in terms of the ergodic occupation measures associated with the controlled Markov process.

Keywords
Related Topics
Physical Sciences and Engineering Engineering Control and Systems Engineering
Preview
Stochastic approximation with ‘controlled Markov’ noise
Authors
,