Socially Guided Intrinsic Motivation for Robot Learning of Motor Skills
This work addresses the challenge of enabling robots to learn complex motor skills efficiently, which is incremental as it integrates existing techniques like imitation learning and intrinsic motivation into a novel framework.
The paper tackles the problem of robot learning of motor skills by combining active intrinsically motivated learning with imitation learning, resulting in an architecture called SGIM-D that efficiently learns high-dimensional continuous sensorimotor inverse models and distributions of parameterised motor policies for varied tasks, as demonstrated in an experiment where a robot arm learns to use a flexible fishing line with improved precision and outcome variety.
This paper presents a technical approach to robot learning of motor skills which combines active intrinsically motivated learning with imitation learning. Our architecture, called SGIM-D, allows efficient learning of high-dimensional continuous sensorimotor inverse models in robots, and in particular learns distributions of parameterised motor policies that solve a corresponding distribution of parameterised goals/tasks. This is made possible by the technical integration of imitation learning techniques within an algorithm for learning inverse models that relies on active goal babbling. After reviewing social learning and intrinsic motivation approaches to action learning, we describe the general framework of our algorithm, before detailing its architecture. In an experiment where a robot arm has to learn to use a flexible fishing line , we illustrate that SGIM-D efficiently combines the advantages of social learning and intrinsic motivation and benefits from human demonstration properties to learn how to produce varied outcomes in the environment, while developing more precise control policies in large spaces.