Title :
Fast learning automata for high-speed real-time applications
Author :
Obaidat, M.S. ; Papadimitriou, G.I. ; Pomportsis, A.S.
Author_Institution :
Dept. of Comput. Sci., Monmouth Univ., West Long Branch, NJ, USA
Abstract :
A new learning automation which is capable of supporting high speed-real-time applications is introduced. The proposed learning automation has unique characteristic: it is capable of performing both probability updating and action selection with a computational complexity which is independent of the number of actions. Apart from its low computational complexity, the proposed automation is capable of achieving a high performance when operating in nonstationary stochastic environments
Keywords :
computational complexity; learning automata; probability; real-time systems; action selection; fast learning automata; high-speed real-time applications; low computational complexity; nonstationary stochastic environments; probability updating; Application software; Computational complexity; Computational intelligence; Computer networks; Computer science; Informatics; Learning automata; Learning systems; Real time systems; Stochastic processes;
Conference_Titel :
Electronics, Circuits and Systems, 2000. ICECS 2000. The 7th IEEE International Conference on
Conference_Location :
Jounieh
Print_ISBN :
0-7803-6542-9
DOI :
10.1109/ICECS.2000.912957
