Abstract
In recent years, in the field of the entertainment robot and the nursing care robot, the method for embedding human emotions to the robot is developed actively. The researches based on not only psychological but also physiological knowledge is also started, and the effect of neuromodulators are gradually making clear in the research field of the brain science. One the other hand, the influence between neuromodulators and meta-parameters of the reinforcement learning system is also reported by some researchers. We have considered a learning method of emotion behaviors of an autonomous mobile robot by using Q-Learning method with the meta-parameters controlled by neuromodulators which is well known in the field of the brain science so far. In this paper, we propose a Q-Learning method with the plural Q-values concerning the maximization and the minimization of rewards and punishments. We aim at the realization of a system that learns complicated emotion behaviors with the behavior selection which has positiveness and negativeness adaptively according to the situation. Furthermore, we also report the result of an experiment by computer simulation to confirm the efficiency of the proposed method.
