Asymptotic behavior of a hierarchical system of learning automata

Thathachar, MAL and Ramachandran, KM (1985) Asymptotic behavior of a hierarchical system of learning automata. In: Information Sciences, 35 (2). pp. 91-110.

PDF pdf.pdf - Published Version Restricted to Registered users only Download (766kB) | Request a copy

Abstract

Learning automata arranged in a two-level hierarchy are considered. The automata operate in a stationary random environment and update their action probabilities according to the linear-reward- -penalty algorithm at each level. Unlike some hierarchical systems previously proposed, no information transfer exists from one level to another, and yet the hierarchy possesses good convergence properties. Using weak-convergence concepts it is shown that for large time and small values of parameters in the algorithm, the evolution of the optimal path probability can be represented by a diffusion whose parameters can be computed explicitly.

Item Type:	Journal Article
Publication:	Information Sciences
Publisher:	Elsevier Science
Additional Information:	The copyright of this article belongs to Elsevier Science
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	28 May 2009 07:27
Last Modified:	19 Sep 2010 05:33
URI:	http://eprints.iisc.ac.in/id/eprint/20477

Actions (login required)

View Item