LR-I Type Learning Algorithm for Variable Hierarchical Structure Learning Automata with S-model Stationary Random Environment at Each Level
Yoshio Mogami, Norio Baba, Nobuhiro Tani · Transactions of the Society of Instrument and Control Engineers · 2000
In this paper, an LR-I type learning algorithm is constructed for variable hierarchical structure learning automata with S-model stationary random environment at each level. The learning propertiy 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.