Show simple item record

dc.contributor.authorLevine, John
dc.contributor.authorNewton, MAHakim
dc.contributor.editorHelder Coelho, Rudi Studer, Michael Wooldridge
dc.date.accessioned2017-05-03T15:43:47Z
dc.date.available2017-05-03T15:43:47Z
dc.date.issued2010
dc.date.modified2013-05-30T01:19:36Z
dc.identifier.refurihttp://www.cubs.buffalo.edu/DAS2010/
dc.identifier.doi10.3233/978-1-60750-606-5-323
dc.identifier.urihttp://hdl.handle.net/10072/45371
dc.description.abstractWe 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.
dc.description.peerreviewedYes
dc.description.publicationstatusYes
dc.format.extent308542 bytes
dc.format.mimetypeapplication/pdf
dc.languageEnglish
dc.language.isoen_US
dc.publisherIOS Press
dc.publisher.placeAmsterdam
dc.publisher.urihttp://ecai2010.appia.pt/
dc.relation.ispartofstudentpublicationN
dc.relation.ispartofconferencenameEuropean Conference on Artificial Intelligence (ECAI2010)
dc.relation.ispartofconferencetitleProceedings of the 2010 conference on ECAI 2010: 19th European Conference on Artificial Intelligence
dc.relation.ispartofdatefrom2010-08-16
dc.relation.ispartofdateto2010-08-20
dc.relation.ispartoflocationLisbon, Portugal
dc.rights.retentionY
dc.subject.fieldofresearchMathematical Sciences not elsewhere classified
dc.subject.fieldofresearchcode019999
dc.titleImplicit Learning of Compiled Macro-Actions for Planning
dc.typeConference output
dc.type.descriptionE1 - Conferences
dc.type.codeE - Conference Publications
gro.rights.copyright© 2011 IOS Press. This is the author-manuscript version of this paper. Reproduced in accordance with the copyright policy of the publisher. Please refer to the publisher website for access to the definitive, published version.
gro.date.issued2010
gro.hasfulltextFull Text
gro.griffith.authorNewton, MAHakim A.


Files in this item

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record