Knowledge Extraction from Reinforcement Learning

Name: Knowledge Extraction from Reinforcement Learning
Creator: Ron Sun
Keywords: 4. Education, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology

Ron Sun

Found an issue? Give us feedback

https://doi.org/10.1...arrow_drop_down

https://doi.org/10.1007/978-3-...

Part of book or chapter of book . 2002 . Peer-reviewed

Data sources: Crossref

https://doi.org/10.1109/ijcnn....

Article . 2003 . Peer-reviewed

Data sources: Crossref

DBLP

Conference object

Data sources: DBLP

https://dx.doi.org/10.1007/978...

Article

Data sources: Microsoft Academic Graph

Knowledge Extraction from Reinforcement Learning

descriptionPublicationkeyboard_double_arrow_right Part of book or chapter of book , Article , Conference object 01 Jan 2002Publisher:Physica-Verlag HDJournal:IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339), volume 4, pages 2,554-2,559

Authors: Ron Sun;

doi: 10.1007/978-3-7908-1803-1_6 , 10.1109/ijcnn.1999.833476

Knowledge Extraction from Reinforcement Learning

- Summary
- Metrics

Abstract

This paper deals with knowledge extraction from reinforcement learners. It addresses two approaches towards knowledge extraction: the extraction of explicit, symbolic rules front neural reinforcement learners; and the extraction of complete plans from such learners. The advantages of such knowledge extraction include: the improvement of learning (especially with the rule extraction approach); and the improvement of the usability of results of learning.

Related Organizations

College of New Jersey
United States
Alabama Agricultural and Mechanical University
United States
University of Missouri
United States

Impact byBIP!

	selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	2
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Top 10%
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average