Discretized Learning Algorithm for Variable Hierarchical Structure Learning Automata with Stationary Random Environment at Each Level
Yoshio Mogami, Norio BABA, Tetsuya HIRONAGA · Transactions of the Society of Instrument and Control Engineers · 2000
In this paper, a learning algorithm is constructed for variable hierarchical structure learning automata with P-model stationary random environments at each level. The learning property of our algorithm is considered theoretically, and it is proved that the probability finding the optimal objective path can be approached 1 as much as possible by using our algorithm. In numerical simulation, the usefulness of our algorithm is shown.