Two Kinds of Training Information for Evaluation Function Learning (1991)
Cached
Download Links
- [ml-www.cs.umass.edu]
- [ml-www.cs.umass.edu]
- [www.cs.umass.edu]
- [www.cs.umass.edu]
- [www-lrn.cs.umass.edu]
- [www-ml.cs.umass.edu]
- DBLP
Other Repositories/Bibliography
by
Paul E. Utgoff
,
Jeffery A. Clouse
| Venue: | In Proceedings of the Ninth Annual Conference on Artificial Intelligence |
| Citations: | 51 - 3 self |
BibTeX
@INPROCEEDINGS{Utgoff91twokinds,
author = {Paul E. Utgoff and Jeffery A. Clouse},
title = {Two Kinds of Training Information for Evaluation Function Learning},
booktitle = {In Proceedings of the Ninth Annual Conference on Artificial Intelligence},
year = {1991},
pages = {596--600},
publisher = {Morgan Kaufmann}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
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.
Citations
| 3341 | Pattern Classification and Scene Analysis - Duda, Hart - 1973 |
| 1060 | Learning to predict by the methods of temporal differences - Sutton - 1988 |
| 545 | Some Studies in Machine Learning using the Game of Checkers - Samuel - 2000 |
| 127 | Learning Machines - Nilsson |
| 44 | A pattern classification approach to evaluation function learning - Lee - 1988 |
| 28 | Connectionist learning of expert preferences by comparison training - Tesauro - 1989 |
| 18 | Learning a preference predicate - Utgoff, Saxena - 1987 |
| 1 | A program to play chess end games. Doctoral dissertation - Huberman - 1968 |
