ML Anthology

Two Kinds of Training Information for Evaluation Function Learning

Paul E. Utgoff, Jeffrey A. Clouse
AAAI 1991 pp. 596-600
/aaai/1991/utgoff1991aaai-two/

Abstract

This paper identifies two fundamentally different kinds of training information for learning search control in terms of an evaluation function. Each kind of training information suggests its own set of methods for learning an evaluation function. The paper shows that one can integrate the methods and learn simultaneously from both kinds of information. 1

PDF AAAI Semantic Scholar

Cite

Text

Utgoff and Clouse. "Two Kinds of Training Information for Evaluation Function Learning." AAAI Conference on Artificial Intelligence, 1991.

Markdown

[Utgoff and Clouse. "Two Kinds of Training Information for Evaluation Function Learning." AAAI Conference on Artificial Intelligence, 1991.](https://mlanthology.org/aaai/1991/utgoff1991aaai-two/)

BibTeX

@inproceedings{utgoff1991aaai-two,
  title     = {{Two Kinds of Training Information for Evaluation Function Learning}},
  author    = {Utgoff, Paul E. and Clouse, Jeffrey A.},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {1991},
  pages     = {596-600},
  url       = {https://mlanthology.org/aaai/1991/utgoff1991aaai-two/}
}