DocumentCode
1308043
Title
On nonlinear reinforcement schemes
Author
Poznyak, A.S. ; Najim, K.
Author_Institution
CINVESTAV-IPN, Mexico City, Mexico
Volume
42
Issue
7
fYear
1997
fDate
7/1/1997 12:00:00 AM
Firstpage
1002
Lastpage
1004
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 probability vector depends on a nonlinear function φ(x). Results concerning the convergence, the convergence rate, and the effect of the function φ(x) are stated. A comparison between the convergence rate of nonlinear and linear reinforcement schemes is presented
Keywords
convergence; finite automata; learning (artificial intelligence); learning automata; learning systems; probability; stochastic automata; action probability vector; convergence rate; correction term; feedback loop; learning automata; linear reinforcement; nonlinear function; nonlinear reinforcement schemes; random environment; Biological systems; Convergence; Feedback loop; Information processing; Learning automata; Learning systems; Probability distribution; Stochastic processes; Stochastic systems; Vectors;
fLanguage
English
Journal_Title
Automatic Control, IEEE Transactions on
Publisher
ieee
ISSN
0018-9286
Type
jour
DOI
10.1109/9.599982
Filename
599982
Link To Document