Continuous action set learning automata for stochastic optimization

Santharam, G. ; Sastry, P. S. ; Thathachar, M. A. L. (1994) Continuous action set learning automata for stochastic optimization Journal of the Franklin Institute, 331 (5). pp. 607-628. ISSN 0016-0032

Full text not available from this repository.

Official URL: http://www.sciencedirect.com/science/article/pii/0...

Related URL: http://dx.doi.org/10.1016/0016-0032(94)90039-6

Abstract

The problem of optimization with noisy measurements is common in many areas of engineering. The only available information is the noise corrupted value of the objective function at any chosen point in the parameter space. One well known method for solving this problem is the stochastic approximation procedure. In this paper we consider an adaptive random search procedure, based on the reinforcement learning paradigm. The learning model presented here generalizes the traditional model of a learning automaton [Narendra and Thathachar, Learning Automata : An Introduction, Prentice Hall, Englewood Cliffs, 1989]. This procedure requires a lesser number of function evaluations at each step compared to the stochastic approximation. The convergence properties of the algorithm are theoretically investigated. Simulation results are presented to show the efficacy of the learning method.

Item Type:Article
Source:Copyright of this article belongs to Elsevier Science.
ID Code:51348
Deposited On:28 Jul 2011 15:01
Last Modified:28 Jul 2011 15:01

Repository Staff Only: item control page