DocumentCode
2868931
Title
A new nonlinear discretized learning automaton with rapid convergence and high accuracy
Author
Vasilakos, Athanasios V. ; Polimenis, Vassilios G. ; Agverinos, Vassilios E.
Author_Institution
Dept. of Comput. Eng., Patras Univ., Greece
fYear
1989
fDate
14-17 Nov 1989
Firstpage
292
Abstract
The authors present a learning automaton which they conjecture to be an ε-optimal variable-structure exponential discretized nonlinear reward-inaction automaton which has better speed of convergence and accuracy than previous discretized reward-inaction schemes. Simulation results are presented that demonstrate this conclusion
Keywords
automata theory; learning systems; ϵ-optimal variable-structure exponential discretized nonlinear reward-inaction automaton; learning automaton; rapid convergence; Convergence; Learning automata; Stochastic processes; Tellurium;
fLanguage
English
Publisher
ieee
Conference_Titel
Systems, Man and Cybernetics, 1989. Conference Proceedings., IEEE International Conference on
Conference_Location
Cambridge, MA
Type
conf
DOI
10.1109/ICSMC.1989.71300
Filename
71300
Link To Document