This paper presents an application of reinforcement learning, an unsupervised learning method, to a biological robot. This study focused on the primitive forward motion of a caterpillar robot to reveal how the robot obtains an optimal motion form in the Q-Learning process. First, this paper verifies that Q-Learning allows the caterpillar robot to move in the forward direction and examines the evolutionary process. Next, this paper discusses the emergence of the motion form using objective rewards. Finally, it examines the emergence of the motion using Q-Learning with subjective rewards in order to clarify the difference between the learning results. This examination provides a novel perspective on human robot interaction (HRI) via reinforcement learning.

No abstract

This note presents an application of reinforcement learning to caterpillar robot locomotion. An excellent advantage of reinforcement learning is that an action can be acquired using only a simple reward. In our previous work, the reward was a forward distance measured using a sensor. This reward was completely an "Objective reward". On the other hand, we have studied using the rewards given by the human's subjective judgment, which is defined as a "Subjective reward". As a result, the "Subjective reward" gave better results than that of the "Objective reward" under specific conditions. The main purpose of this study is to investigate the teaching methods of human being, which is the main factor that gives better results than "Objective reward". This note discusses the good teacher who gives an excellent "Subjective reward". The results show that the human being gives reward in consideration of not only distance but also motion forms, and can give better results than that of the "Objective reward".