Finite time analysis of the pursuit algorithm for learning automata

Author

Rajaraman, K. ; Sastry, P.S.

Author_Institution

Dept. of Electr. Eng., Indian Inst. of Sci., Bangalore, India

Volume

26

Issue

4

fYear

1996

fDate

8/1/1996 12:00:00 AM

Firstpage

590

Lastpage

598

Abstract

The problem of analyzing the finite time behavior of learning automata is considered. This problem involves the finite time analysis of the learning algorithm used by the learning automaton and is important in determining the rate of convergence of the automaton. In this paper, a general framework for analyzing the finite time behavior of the automaton learning algorithms is proposed. Using this framework, the finite time analysis of the Pursuit Algorithm is presented. We have considered both continuous and discretized forms of the pursuit algorithm. Based on the results of the analysis, we compare the rates of convergence of these two versions of the pursuit algorithm. At the end of the paper, we also compare our framework with that of Probably Approximately Correct (PAC) learning

Keywords

finite automata; learning automata; learning systems; PAC learning; Probably Approximately Correct; finite time behavior; learning automata; pursuit algorithm; rates of convergence; Algorithm design and analysis; Application software; Convergence; Decision making; Game theory; Iterative algorithms; Learning automata; Learning systems; Pattern recognition; Pursuit algorithms;

fLanguage

English

Journal_Title

Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on

Publisher

ieee

ISSN

1083-4419

Type

jour

DOI

10.1109/3477.517033

Filename

517033