Learning to Control a Dynamic Physical System

Book One

Volume

Proceedings of the AAAI Conference on Artificial Intelligence, 6

Machine Learning and Knowledge Acquisition

This paper presents an approach to learning to control a dynamic physical system. The approach has been implemented in a program named CART, and applied to a simple physical system studied previously by several researchers. Experiments illustrate that a control method is learned in about 16 trials, an improvement over previous learning programs.