ON NONLINEAR REINFORCEMENT SCHEMES

Authors
POZNYAK AS NAJIM K
Citation
As. Poznyak et K. Najim, ON NONLINEAR REINFORCEMENT SCHEMES, IEEE transactions on automatic control, 42(7), 1997, pp. 1002-1004
Citations number
8
Categorie Soggetti
Controlo Theory & Cybernetics","Robotics & Automatic Control","Engineering, Eletrical & Electronic
Journal title
IEEE transactions on automatic control → ACNP
ISSN journal
00189286
Volume
42
Issue
7
Year of publication
1997
Pages
1002 - 1004
Database
ISI
SICI code
0018-9286(1997)42:7<1002:ONRS>2.0.ZU;2-L
Abstract
This paper deals with the analysis of nonlinear reinforcement schemes for learning automata. The learning automaton is connected in feedback loop to a random environment. The correction term of the action proba bility vector depends on a nonlinear function phi(x). Results concerni ng the convergence, the convergence rate, and the effect of the functi on phi(x) are stated. A comparison between the convergence rate of non linear and linear reinforcement schemes is presented.