Learning behaviors of the hierarchical structure stochastic automata under the nonstationary multiteacher environments and their applications to intelligent robot manipulators

Learning behaviors of the hierarchical structure stochastic automata operating in a nonstationary multiteacher environment are considered. It is shown that an extended form of the algorithm proposed by Thathachar and Ramakrishnan ensures absolute expediency under some condition. As a practical application of the hierarchical structure stochastic automata, an intelligent behavior of robot manipulators going through a maze having a large number of gates that close with unknown rejecting probabilities is also considered. It is shown that the hierarchical structure stochastic automata can be successfully utilized to let robot manipulators gradually find the best way in the maze.