Implicit Learning of Macro-Actions for Planning

M. A. H. Newton, J. Levine

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

2 Citations (Scopus)

Abstract

We build a comprehensive macro-learning system and contribute in three different dimensions that have previously not been addressed adequately. Firstly, we learn macro-sets considering implicitly the interactions between constituent macros. Secondly, we effectively learn macros that are not found in given example plans. Lastly, we improve or reduce degradation of plan-length when macros are used; note, our main objective is to achieve fast planning. Our macro-learning system significantly outperforms a very recent macro-learning method both in solution speed and plan length.
Original languageEnglish
Title of host publicationProceedings of the 2010 conference on ECAI 2010
Subtitle of host publication19th European Conference on Artificial Intelligence
Place of PublicationNew York
Pages323-328
Number of pages6
DOIs
Publication statusPublished - 1 Aug 2010

Keywords

  • artificial intelligence
  • implicit learning

Fingerprint Dive into the research topics of 'Implicit Learning of Macro-Actions for Planning'. Together they form a unique fingerprint.

Cite this