Reinforcement Learning for Robotic Reaching and Grasping

摘要

INTRODUCTION In a laboratory situation, a primate learns to perform the task designated by the experimenter through a reward/penalty or reinforcement-based paradigm. This reinforcement information, however, is extremely sparse relative to all of the things the monkey must do in order to obtain a reward. Even with the simplest tasks (e.g. reaching to grasp a handle), a monkey has many different motor acts that are available, from which he must select some sequence. When a reinforcement signal is provided, he must somehow infer the critical elements of his actions that caused him to receive the reward, so that these elements may be repeated the next time that the same situation arises. Despite this very limited amount of information, the monkey is often able to learn the desired task. Within the robotics domain, we find a somewhat similar problem, in that it is typically difficult to specify a robust motor program. A very common technique is to specify in great detail the trajectory th