Automatically Learning HTN Methods from Landmarks

Hierarchical Task Network (HTN) planning usually requires a domain engineer to provide manual input about how to decompose a planning problem. Even HTN-MAKER, a well-known method-learning algorithm, requires a domain engineer to annotate the tasks with information about what to learn. We introduce C...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the ... International Florida Artificial Intelligence Research Society Conference Vol. 37
Main Authors Ruoxi Li, Dana Nau, Mark Roberts, Morgan Fine-Morris
Format Journal Article
LanguageEnglish
Published LibraryPress@UF 12.05.2024
Online AccessGet full text
ISSN2334-0754
2334-0762
2334-0762
DOI10.32473/flairs.37.1.135625

Cover

Abstract Hierarchical Task Network (HTN) planning usually requires a domain engineer to provide manual input about how to decompose a planning problem. Even HTN-MAKER, a well-known method-learning algorithm, requires a domain engineer to annotate the tasks with information about what to learn. We introduce CURRICULAMA, an HTN method learning algorithm that completely automates the learning process. It uses landmark analysis to compose annotated tasks and leverages curriculum learning to order the learning of methods from simpler to more complex. This eliminates the need for manual input, resolving a core issue with HTN-MAKER. We prove CURRICULAMA's soundness, and show experimentally that it has a substantially similar convergence rate in learning a complete set of methods to HTN-MAKER.
AbstractList Hierarchical Task Network (HTN) planning usually requires a domain engineer to provide manual input about how to decompose a planning problem. Even HTN-MAKER, a well-known method-learning algorithm, requires a domain engineer to annotate the tasks with information about what to learn. We introduce CURRICULAMA, an HTN method learning algorithm that completely automates the learning process. It uses landmark analysis to compose annotated tasks and leverages curriculum learning to order the learning of methods from simpler to more complex. This eliminates the need for manual input, resolving a core issue with HTN-MAKER. We prove CURRICULAMA's soundness, and show experimentally that it has a substantially similar convergence rate in learning a complete set of methods to HTN-MAKER.
Author Dana Nau
Mark Roberts
Morgan Fine-Morris
Ruoxi Li
Author_xml – sequence: 1
  fullname: Ruoxi Li
  organization: University of Maryland
– sequence: 2
  fullname: Dana Nau
– sequence: 3
  fullname: Mark Roberts
– sequence: 4
  fullname: Morgan Fine-Morris
BookMark eNo9kMtOwzAQRS1UJErpF7DJDyT4GdvLqgJaKcCmrK3xqwTSpHJSof49UYO6mqtZnDtz7tGs7dqA0CPBBaNcsqfYQJ36gsmCFISJkoobNKeM8RzLks6uWfA7tOz72mLOpSi1EHNEVqehO8BQO2iac1YFSG3d7rPN7j17C8NX5_sspu6QVdD6A6Sf_gHdRmj6sPyfC_T58rxbb_Lq43W7XlW5o1SIXJXgowfA2ikmolbeaWmVkiwSTChIwFG7EMBiVnosHRPUBs-dpSVgB2yBthPXd_Btjqke28-mg9pcFl3aG0jj3U0w1inPJSbOWcW9ldYGorSOY_CgmR1ZfGKd2iOcf8dXr0CCzcWimSwaJg0xk0X2B31_aaM
ContentType Journal Article
DBID ADTOC
UNPAY
DOA
DOI 10.32473/flairs.37.1.135625
DatabaseName Unpaywall for CDI: Periodical Content
Unpaywall
DOAJ Directory of Open Access Journals
DatabaseTitleList
Database_xml – sequence: 1
  dbid: DOA
  name: DOAJ Directory of Open Access Journals
  url: https://www.doaj.org/
  sourceTypes: Open Website
– sequence: 2
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
EISSN 2334-0762
ExternalDocumentID oai_doaj_org_article_bc8d4701ccb84db7bbe1899f7bbda93b
10.32473/flairs.37.1.135625
GroupedDBID ADTOC
ALMA_UNASSIGNED_HOLDINGS
GROUPED_DOAJ
UNPAY
ID FETCH-LOGICAL-c2255-86adfdaa09c835f98dc97b8873f1012a7a0f9ceeab036d07c352bed4cb26a0ca3
IEDL.DBID UNPAY
ISSN 2334-0754
2334-0762
IngestDate Fri Oct 03 12:41:23 EDT 2025
Mon Sep 15 10:19:15 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Language English
License cc-by-nc
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2255-86adfdaa09c835f98dc97b8873f1012a7a0f9ceeab036d07c352bed4cb26a0ca3
OpenAccessLink https://proxy.k.utb.cz/login?url=http://doi.org/10.32473/flairs.37.1.135625
ParticipantIDs doaj_primary_oai_doaj_org_article_bc8d4701ccb84db7bbe1899f7bbda93b
unpaywall_primary_10_32473_flairs_37_1_135625
PublicationCentury 2000
PublicationDate 2024-05-12
PublicationDateYYYYMMDD 2024-05-12
PublicationDate_xml – month: 05
  year: 2024
  text: 2024-05-12
  day: 12
PublicationDecade 2020
PublicationTitle Proceedings of the ... International Florida Artificial Intelligence Research Society Conference
PublicationYear 2024
Publisher LibraryPress@UF
Publisher_xml – name: LibraryPress@UF
SSID ssib044756955
ssib059229545
Score 2.258325
Snippet Hierarchical Task Network (HTN) planning usually requires a domain engineer to provide manual input about how to decompose a planning problem. Even HTN-MAKER,...
SourceID doaj
unpaywall
SourceType Open Website
Open Access Repository
SummonAdditionalLinks – databaseName: DOAJ Directory of Open Access Journals
  dbid: DOA
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV09T8MwELVQF2BAIECUL2VgdZvEjh2PBVFVCDq1UjfrbMcMlLTqh1D_PWcngm4sbFEkO8k7x_dOtt8j5KHyUoGUgipgOeXgLC0dz6ligXykHquQuEF2LEZT_jIrZntWX2FPWCMP3ADXNxbbyjSz1pTcGWlMlWGN4PHCgWImzL5pqfaKKRxJQcVOqN8Tl4UKrtXRsThnjFPMk7yRIEI-IVnfz8PiSY_JXhaMIEQwzo4S_sfkcFsvYfcF8_le3hmekpOWMCaD5kXPyEFVn5NssN0sotgqttglrUjqezKajJO36Am9TsLBkeQVavcJq4_1BZkOnydPI9qaH1CLv1hBSwHOO4BUWSRJXpXOKmlwSmA-SHKBhNQrzHBgMAe5VFpkUqZy3JpcQGqBXZJOvairK5J4oTLIhBPWl9yKEqw33rEKmYJjThVd8hi-VS8bfQsdFKfjDYyDbuOg_4pDl9AfpH56wgojAqwbgDWTOtMNwNf_8dAbcpQjyQir-Vl-Szqb1ba6Q5KwMfdxPHwD4825mg
  priority: 102
  providerName: Directory of Open Access Journals
Title Automatically Learning HTN Methods from Landmarks
URI http://doi.org/10.32473/flairs.37.1.135625
https://doaj.org/article/bc8d4701ccb84db7bbe1899f7bbda93b
UnpaywallVersion publishedVersion
Volume 37
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVAON
  databaseName: DOAJ Directory of Open Access Journals
  customDbUrl:
  eissn: 2334-0762
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssib059229545
  issn: 2334-0754
  databaseCode: DOA
  dateStart: 20210101
  isFulltext: true
  titleUrlDefault: https://www.doaj.org/
  providerName: Directory of Open Access Journals
– providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2334-0762
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssib044756955
  issn: 2334-0754
  databaseCode: M~E
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA66HdSDP1Bx_hg9eM1smy5pjlMmQ9zwsME8lZek8bDZjf1A5sG_3Ze2bAMR9FJCKWn58tr3PV76fYTcplZIEIJTCSykERhNYxOFVDJHPnyLVUi-QbbHO4PoadgcbmRyttr3mOkFu7Nj19ZoMNEInEUDsvVdUuVN5N0VUh30XlqvuXsciyjmvmgz5mEhMfTbLKVE_wHZW2ZTWH3AeLyVVx6PCoOieS5H6LaTjBrLhWroz59ijX945GNyWNJLr1XEwwnZSbNTErSWi0kuzYr3X3mlpOqb1-n3vG7uID333G8m3jNk5h1mo_kZGTy2-w8dWlolUI0vZJPGHIw1AL7USKmsjI2WQuEHhFkn4AUCfCsxH4LCjGV8oZF3qdREWoUcfA3snFSySZZeEM9yGUDADdc2jjSPQVtlDUuRVxhmZLNG7h1yybRQw0icPnV-AkFIynBPlMYVF36gtYojo4RSaYCVncWBAclUjdA17uuZsB7JEUwKBBMmkiApELz85_VXZD9E9uHa_EF4TSqL2TK9QfawUPW86sZj96tdL0PoG9cowPE
linkProvider Unpaywall
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA66HdSDP1Bx_qIHr5lt0ybNcYpjiA4PG8xTeUkaD85ubB0y_3pf2rINRNBbKCUtX1_yvsdLv4-Qm8wKCUJwKoGFNAKjaWKikErmyIdvsQopD8j2eW8YPY7i0VomZ6N9j5lesFs7dm2NNhPtwFk0IFvfJk0eI-9ukOaw_9J5Ld3jWEQx90XrMQ8riaHfZqkl-vfIziKfwvITxuONvNI9qAyK5qUcoTtO8t5eFKqtv36KNf7hlQ_Jfk0vvU4VD0dkK8uPSdBZFJNSmhWfv_RqSdU3rzfoe8-lg_Tcc7-ZeE-Qmw-Yvc9PyLD7MLjv0doqgWpckDFNOBhrAHypkVJZmRgthcINhFkn4AUCfCsxH4LCjGV8oZF3qcxEWoUcfA3slDTySZ6dEc9yGUDADdc2iTRPQFtlDcuQVxhmZNwidw65dFqpYaROn7q8gCCkdbinSuMXF36gtUoio4RSWYCVncWBAclUi9AV7quZsB4pEUwrBFMm0iCtEDz_5_0XZDdE9uHa_EF4SRrFbJFdIXso1HUdNt_dHL7L
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Automatically+Learning+HTN+Methods+from+Landmarks&rft.jtitle=Proceedings+of+the+International+Florida+Artificial+Intelligence+Research+Society+Conference&rft.au=Ruoxi+Li&rft.au=Dana+Nau&rft.au=Mark+Roberts&rft.au=Morgan+Fine-Morris&rft.date=2024-05-12&rft.pub=LibraryPress%40UF&rft.issn=2334-0754&rft.eissn=2334-0762&rft.volume=37&rft_id=info:doi/10.32473%2Fflairs.37.1.135625&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_bc8d4701ccb84db7bbe1899f7bbda93b
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2334-0754&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2334-0754&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2334-0754&client=summon