DOI

A new stochastic approximation algorithm with input perturbation for self-learning is designed with test perturbations and has certain useful properties, such as consistency of estimates tinder almost arbitrary perturbations and preservation of simplicity and performance with the growing size of the state space and increasing number of classes. An example. oil computer-aided modeling of learning is given to illustrate the performance of the algorithm.

Язык оригиналаАнглийский
Страницы (с-по)1239-1248
Число страниц10
ЖурналAutomation and Remote Control
Том66
Номер выпуска8
DOI
СостояниеОпубликовано - 2005

ID: 5014772