Experimental Results from an Evaluation of Algorithms That Learn to Control Dynamic Systems

Abstract

This paper reports on experiments performed with a variety of algorithms that have been used for the task of learning to control dynamic systems. It compares their speed, reliability and the assumptions about the problem domain which must be made in order for them to work. We describe a promising new method which combines induction with reinforcement learning. The output of this method is a set of control rules which are fast, reliable and, most importantly, more readable than the parameters and weights which constitute the knowledge of a pure reinforcement system. Finally, some open questions are presented.

Cite

Text

Sammut. "Experimental Results from an Evaluation of Algorithms That Learn to Control Dynamic Systems." International Conference on Machine Learning, 1988. doi:10.1016/B978-0-934613-64-4.50049-9

Markdown

[Sammut. "Experimental Results from an Evaluation of Algorithms That Learn to Control Dynamic Systems." International Conference on Machine Learning, 1988.](https://mlanthology.org/icml/1988/sammut1988icml-experimental/) doi:10.1016/B978-0-934613-64-4.50049-9

BibTeX

@inproceedings{sammut1988icml-experimental,
  title     = {{Experimental Results from an Evaluation of Algorithms That Learn to Control Dynamic Systems}},
  author    = {Sammut, Claude},
  booktitle = {International Conference on Machine Learning},
  year      = {1988},
  pages     = {437-443},
  doi       = {10.1016/B978-0-934613-64-4.50049-9},
  url       = {https://mlanthology.org/icml/1988/sammut1988icml-experimental/}
}