Machine Learning for Robots A Comparison of Di erent Paradigms

For robots to be truly exible they need to be able to learn to adapt to partially known or dynamic environments to teach themselves new tasks and to compensate for sensor and e ector defects The problem of robot learning has been an intensively stud ied research topic over the last decade In this paper we critically examine four major formulations of the robot learning problem inductive concept learning explanation based learning reinforcement learning and evolutionary learning We describe some well known examples of systems that t under each formulation and discuss their strengths and limitations