Two Kinds of Training Information For Evaluation Function Learning


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.

Extracted Key Phrases

3 Figures and Tables


Citations per Year

76 Citations

Semantic Scholar estimates that this publication has 76 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@inproceedings{Utgoff1991TwoKO, title={Two Kinds of Training Information For Evaluation Function Learning}, author={Paul E. Utgoff and Jeffrey A. Clouse}, booktitle={AAAI}, year={1991} }