Finite time analysis of the pursuit algorithm for learning automata

Authors:
K. Rajaraman;P. S. Sastry
Affiliations:
Dept. of Electr. Eng., Indian Inst. of Sci., Bangalore;-
Venue:
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Year:
1996

Citing 0
Cited 5

Stochastic learning-based weak estimation of multinomial random variables and its applications to pattern recognition in non-stationary environments

Pattern Recognition
Sampled fictitious play for approximate dynamic programming

Computers and Operations Research
On utilizing stochastic learning weak estimators for training and classification of patterns with non-stationary distributions

KI'05 Proceedings of the 28th annual German conference on Advances in Artificial Intelligence
Approximate stochastic annealing for online control of infinite horizon Markov decision processes

Automatica (Journal of IFAC)
On incorporating the paradigms of discretization and Bayesian estimation to create a new family of pursuit learning automata

Applied Intelligence

Quantified Score

Hi-index	0.00

Visualization

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