ML Anthology

Learning to Control a Dynamic Physical System

Margaret E. Connell, Paul E. Utgoff
AAAI 1987 pp. 456-460
doi:10.1111/j.1467-8640.1987.tb00219.x /aaai/1987/connell1987aaai-learning/

Abstract

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.

PDF AAAI Semantic Scholar

Cite

Text

Connell and Utgoff. "Learning to Control a Dynamic Physical System." AAAI Conference on Artificial Intelligence, 1987. doi:10.1111/j.1467-8640.1987.tb00219.x

Markdown

[Connell and Utgoff. "Learning to Control a Dynamic Physical System." AAAI Conference on Artificial Intelligence, 1987.](https://mlanthology.org/aaai/1987/connell1987aaai-learning/) doi:10.1111/j.1467-8640.1987.tb00219.x

BibTeX

@inproceedings{connell1987aaai-learning,
  title     = {{Learning to Control a Dynamic Physical System}},
  author    = {Connell, Margaret E. and Utgoff, Paul E.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1987},
  pages     = {456-460},
  doi       = {10.1111/j.1467-8640.1987.tb00219.x},
  url       = {https://mlanthology.org/aaai/1987/connell1987aaai-learning/}
}