ML Anthology

An Analysis of Learning to Plan as a Search Problem

Jonathan Gratch, Gerald DeJong
ICML 1992 pp. 179-188
doi:10.1016/B978-1-55860-247-2.50028-0 /icml/1992/gratch1992icml-analysis/

Abstract

Composer is one of a growing number of techniques for learning to plan. Like other approaches, it embodies a number of simplifications to overcome the complexities of learning. These simplifications introduce tradeoffs between learning efficiency and effectiveness. In this paper we relate Composer to our general framework of simplifications for learning to plan [Gratch92a]. This discussion illustrates how such a framework may be used to analyze a particular approach, highlighting the learning system's strengths and weaknesses.

ICML Semantic Scholar

Cite

Text

Gratch and DeJong. "An Analysis of Learning to Plan as a Search Problem." International Conference on Machine Learning, 1992. doi:10.1016/B978-1-55860-247-2.50028-0

Markdown

[Gratch and DeJong. "An Analysis of Learning to Plan as a Search Problem." International Conference on Machine Learning, 1992.](https://mlanthology.org/icml/1992/gratch1992icml-analysis/) doi:10.1016/B978-1-55860-247-2.50028-0

BibTeX

@inproceedings{gratch1992icml-analysis,
  title     = {{An Analysis of Learning to Plan as a Search Problem}},
  author    = {Gratch, Jonathan and DeJong, Gerald},
  booktitle = {International Conference on Machine Learning},
  year      = {1992},
  pages     = {179-188},
  doi       = {10.1016/B978-1-55860-247-2.50028-0},
  url       = {https://mlanthology.org/icml/1992/gratch1992icml-analysis/}
}