Learning a Set of Primitive Actions with an Uninterpreted Sensorimotor Apparatus

Pierce, David R.

doi:10.1016/B978-1-55860-200-7.50070-2

Learning a Set of Primitive Actions with an Uninterpreted Sensorimotor Apparatus

David R. Pierce

ICML 1991 pp. 338-342

doi:10.1016/B978-1-55860-200-7.50070-2 /icml/1991/pierce1991icml-learning/

Abstract

We demonstrate a learning method by which a mobile robot may analyze an initially uninterpreted sensorimotor apparatus and produce a useful characterization of its set of actions. We apply the method to the case of a simulated robot with an array of 16 range finders and a “tank-style― motor apparatus. The robot learns a set of primitive actions allowing it to make pure turn and travel actions.

ICML Semantic Scholar

Cite

Text

Pierce. "Learning a Set of Primitive Actions with an Uninterpreted Sensorimotor Apparatus." International Conference on Machine Learning, 1991. doi:10.1016/B978-1-55860-200-7.50070-2

Markdown

[Pierce. "Learning a Set of Primitive Actions with an Uninterpreted Sensorimotor Apparatus." International Conference on Machine Learning, 1991.](https://mlanthology.org/icml/1991/pierce1991icml-learning/) doi:10.1016/B978-1-55860-200-7.50070-2

BibTeX

@inproceedings{pierce1991icml-learning,
  title     = {{Learning a Set of Primitive Actions with an Uninterpreted Sensorimotor Apparatus}},
  author    = {Pierce, David R.},
  booktitle = {International Conference on Machine Learning},
  year      = {1991},
  pages     = {338-342},
  doi       = {10.1016/B978-1-55860-200-7.50070-2},
  url       = {https://mlanthology.org/icml/1991/pierce1991icml-learning/}
}