Learning to control a dynamic physical system
Margaret E. Connell, Emmanuel J. Connell, Paul E. Utgoff · Computational Intelligence · 1987
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.