|
Abstract : |
For robots to be truly flexible, they need to be able to learn to adapt to partiallyknown or dynamic environments, to teach themselves new tasks, and to compensate for sensor and effector defects. The problem of robot learning has been an intensively studied research topic over the last decade. In this paper we critically examine four major formulations of the robot learning problem: inductive concept learning, explanationbased learning, reinforcement learning, and evolutionary learning. We describe some well-known examples of systems that fit under each formulation, and discuss their strengths and limitations. 1, |
