Abstract
Mental State Transition Network which consists of mental states connected one another is a basic concept of approximating to human psychological and mental responses. It can represent transition from an emotional state to other one with stimulus by calculating Emotion Generating Calculations method. In this paper, the agent using Mental State Transition Network can interact with human to realize smooth communication by reinforcement learning methods. Some experimental results can show the variance of human delicate emotion. The proposed technique can be expected to be an emotional oriented interface in case of treatment of mental disorder.
