Premium
Learning to control a dynamic physical system
Author(s) -
Connell Margaret E.,
Connell E.,
Utgoff Paul E.
Publication year - 1987
Publication title -
computational intelligence
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.353
H-Index - 52
eISSN - 1467-8640
pISSN - 0824-7935
DOI - 10.1111/j.1467-8640.1987.tb00219.x
Subject(s) - computer science , control (management) , simple (philosophy) , artificial intelligence , machine learning , physical system , control system , engineering , philosophy , physics , epistemology , quantum mechanics , electrical engineering
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.