Title :
A new learning algorithm for the hierarchical structure learning automata operating in the general nonstationary multiteacher environment
Author :
Baba, Norio ; Mogami, Yoshio
Author_Institution :
Osaka Kyoiku Univ., Japan
Abstract :
A new algorithm of the hierarchical structure learning automata operating in the nonstationary multiteacher environment is proposed. It is shown that the proposed algorithm ensures convergence with probability 1 to the optimal path under certain type of nonstationary multiteacher environment.
Keywords :
learning automata; optimisation; probability; general nonstationary multiteacher environment; hierarchical structure learning automata; learning algorithm; relative reward strength algorithm;
Conference_Titel :
SICE 2003 Annual Conference
Conference_Location :
Fukui, Japan
Print_ISBN :
0-7803-8352-4
