抄録
Conventional artificial intelligence (AI) system has been criticized for its brittleness under dynamically changing environments. Therefore, in recent years much attention has been focused on the reactive planning approach such as behavior-based AI, new AI, animat approach and so on. However, in behavior-based AI approaches, the arbitration among competence modules is still an open question. On the other hand, biological information processing systems have various interesting characteristics viewed from the engineering standpoint. Among them, the immune system plays an important role in maintaining its own system against hostile environments. Based on this consideration, we have been investigating a new decentralized consensus-making system for the behavior arbitration of autonomous mobile robots inspired from the idiotypic network hypothesis in immunology. In this paper, we propose a new reinforcement learning method using advantage of the proposed network architecture. To confirm the validity of our proposed method, we carried out some simulations.
