Framework of simplifications in learning to plan

Jonathan Gratch, Gerald DeJong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Learning shows great promise to extend the generality and effectiveness of planning techniques. Research in this area has generated an impressive battery of techniques and a growing body of empirical successes. Unfortunately the formal properties of these systems are not well understood. This is highlighted by a growing corpus of demonstrations where learning actually degrades planning performance. In this paper we view learning to plan as a search problem. We argue that the complexity of this search precludes a general solution and can only be approached by making simplifying assumptions. We discuss the frequently unarticulated commitments which underly current learning approaches. From these we assemble a framework of simplifications which a learning planner can draw upon. These simplifications improve learning efficiency but not without tradeoffs.

Original languageEnglish (US)
Title of host publicationProc 1 Int Conf Artif Intell Plann Syst
PublisherPubl by Morgan Kaufmann Publ Inc
Pages78-87
Number of pages10
ISBN (Print)155860250X
StatePublished - Dec 1 1992
EventProceedings of the 1st International Conference on Artificial Intelligence Planning Systems - College Park, MD, USA
Duration: Jun 15 1992Jun 17 1992

Publication series

NameProc 1 Int Conf Artif Intell Plann Syst

Other

OtherProceedings of the 1st International Conference on Artificial Intelligence Planning Systems
CityCollege Park, MD, USA
Period6/15/926/17/92

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Framework of simplifications in learning to plan'. Together they form a unique fingerprint.

Cite this