Back to Search Start Over

Learning automata with continuous input and changing number of actions

Authors :
Kaddour Najim
Alexander S. Poznyak
Source :
International Journal of Systems Science. 27:1467-1472
Publication Year :
1996
Publisher :
Informa UK Limited, 1996.

Abstract

The behaviour of a stochastic automaton operating in an S-model environment is described. The environment response takes an arbitrary value in the closed segment [0, 1] (continuous response). The learning automaton uses a reinforcement scheme to update its action probabilities on the basis of the reaction of the environment. The complete set of actions is divided into a collection of non-empty subsets. The action set is changing from instant to instant. Each action set is selected according to a given probability distribution. Convergence and convergence rate results are presented. These results have been derived using quasimartingales theory.

Details

ISSN :
14645319 and 00207721
Volume :
27
Database :
OpenAIRE
Journal :
International Journal of Systems Science
Accession number :
edsair.doi...........86e18ed75c6ada7470dec5c895028485
Full Text :
https://doi.org/10.1080/00207729608929353