Title :
IJA Automaton: Expediency and ε-optimality Properties
Author :
Iraji, R. ; Manzuri-Shalmani, M.T. ; Jamalian, A.H. ; Beigy, H.
Author_Institution :
Dept. of Comput. Eng., Sharif Univ. of Technol., Tehran
Abstract :
In this paper, we present a new fixed structure learning automaton (FSSA), called IJA, and study its steady state behavior in stationary environments. The proposed automaton characterizes by star shaped transition diagram and each branch of the star contains N states associated with a particular action. This new automaton is an improvement of the Krinsky FSSA and not only ε-optimal and expedient, but also converges to the optimal action faster than the old one
Keywords :
diagrams; learning automata; IJA automaton; fixed structure learning automaton; steady state behavior; transition diagram; Biological system modeling; Biology computing; Feedback; Learning automata; Power engineering and energy; Power engineering computing; Pursuit algorithms; Steady-state; Stochastic processes; Tellurium; ε-optimality; FSSA; Learning automata;
Conference_Titel :
Cognitive Informatics, 2006. ICCI 2006. 5th IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
1-4244-0475-4
DOI :
10.1109/COGINF.2006.365556
