ML Anthology

Learning to Solve Complex Tasks for Reactive Systems (Extended Abstract)

Mario Martín, Ulises Cortés
ECML-PKDD 1995 pp. 315-318
doi:10.1007/3-540-59286-5_76 /ecmlpkdd/1995/martin1995ecml-learning/

Abstract

This research has lead us to show that it is possible, for reactive systems, to learn how to solve complex tasks. The task proposed in the “blocks world”, considering the initial set of actions the system knows, is not currently resolvable by any other direct learning method. The success of our proposal is due to the use of a learning mechanism robust to ambiguous information, that can improve the abilities of the system, learning new behaviors to solve general tasks.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Martín and Cortés. "Learning to Solve Complex Tasks for Reactive Systems (Extended Abstract)." European Conference on Machine Learning, 1995. doi:10.1007/3-540-59286-5_76

Markdown

[Martín and Cortés. "Learning to Solve Complex Tasks for Reactive Systems (Extended Abstract)." European Conference on Machine Learning, 1995.](https://mlanthology.org/ecmlpkdd/1995/martin1995ecml-learning/) doi:10.1007/3-540-59286-5_76

BibTeX

@inproceedings{martin1995ecml-learning,
  title     = {{Learning to Solve Complex Tasks for Reactive Systems (Extended Abstract)}},
  author    = {Martín, Mario and Cortés, Ulises},
  booktitle = {European Conference on Machine Learning},
  year      = {1995},
  pages     = {315-318},
  doi       = {10.1007/3-540-59286-5_76},
  url       = {https://mlanthology.org/ecmlpkdd/1995/martin1995ecml-learning/}
}