A new learning algorithm for the hierarchical structure learning automata operating in the nonstationary S-model random environm

An extended algorithm of the relative reward strength algorithm is proposed. It is shown that the proposed algorithm ensures the convergence with probability 1 to the optimal path under the certain type of nonstationary environment. Several computer simulation results confirm the effectiveness of the proposed algorithm.

• Type: Journal
• Year: 2002
• Where: TSMC
• Authors: Norio Baba, Yoshio Mogami
• Keywords: Algorithm, Extended Algorithm, Reward Strength Algorithm, TSMC 2002