Empirical results from applying machine learning techniques to planning

McCluskey, T.L. (1990) Empirical results from applying machine learning techniques to planning. In: IEE Colloquium on Machine Learning. IEEE Press, 6/1-6/3.

Metadata only available from this repository.

Abstract

Outlines an experimental machine learning implementation, called `FM', that applies both explanation based learning and similarity-based learning to AI planners. The system shell of FM contains techniques for learning application-dependent heuristics, through the experience of using a performance component (a planner) in that application. An application domain is supplied by specifying a set of action schemas, and environmental facts and rules. FM is then fed an initial state, and a sequence of tasks within this application, roughly in ascending order of complexity, which it is expected to solve. After each task has been solved, the system analyses the planning trace, allowing it to learn from experience.

Item Type:	Book Chapter
Additional Information:	Paper presented at IEEE Colloquium on Machine Learning, London, 28th June 1990
Subjects:	T Technology > T Technology (General)
Schools:	School of Computing and Engineering School of Computing and Engineering > Pedagogical Research Group School of Computing and Engineering > High-Performance Intelligent Computing School of Computing and Engineering > High-Performance Intelligent Computing > Planning, Autonomy and Representation of Knowledge School of Computing and Engineering > High-Performance Intelligent Computing > Planning, Autonomy and Representation of Knowledge
Related URLs:	Author
Depositing User:	Cherry Edmunds
Date Deposited:	16 Jul 2010 13:43
Last Modified:	28 Aug 2021 10:58
URI:	http://eprints.hud.ac.uk/id/eprint/8150

Downloads

Repository Staff Only: item control page

View Item