{"id":"https://openalex.org/W2107628283","doi":null,"title":"Automated State Abstraction for Options using the U-Tree Algorithm","display_name":"Automated State Abstraction for Options using the U-Tree Algorithm","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W2107628283","mag":"2107628283"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.107.4380","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.107.4380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.tecn.upf.es/~jonsson/nips01.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086943516","display_name":"Anders J\u00f6nsson","orcid":"https://orcid.org/0000-0002-5756-7847","observed_orcids":["https://orcid.org/0000-0002-5756-7847"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anders J\u00f6nsson","raw_affiliation_strings":["Dept of Computer Science, University of Massachusetts, Amherst, MA"],"raw_orcid":"https://orcid.org/0000-0002-5756-7847","affiliations":[{"raw_affiliation_string":"Dept of Computer Science, University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808068","display_name":"Andrew G. Barto","orcid":"https://orcid.org/0000-0002-3581-1896","observed_orcids":["https://orcid.org/0000-0002-3581-1896"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew G. Barto","raw_affiliation_strings":["Dept of Computer Science, University of Massachusetts, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept of Computer Science, University of Massachusetts, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.7941,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.74400261,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":"13","issue":null,"first_page":"1054","last_page":"1060"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/options-framework","display_name":"options framework","score":0.7960000038146973},{"id":"https://openalex.org/keywords/hierarchical-reinforcement-learning","display_name":"hierarchical reinforcement learning","score":0.8180000185966492},{"id":"https://openalex.org/keywords/state-abstraction","display_name":"state abstraction","score":0.8730000257492065},{"id":"https://openalex.org/keywords/feature-space-representation","display_name":"feature space representation","score":0.4560000002384186},{"id":"https://openalex.org/keywords/subtasks","display_name":"subtasks","score":0.37299999594688416}],"concepts":[{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.8888270854949951},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986481785774231},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.7491269707679749},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.6634650230407715},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6626464128494263},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.556534469127655},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5156118273735046},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5127623677253723},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46885761618614197},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45709601044654846},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44304734468460083},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.4395824074745178},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.41249480843544006},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25279563665390015},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.16373932361602783},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14538556337356567},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08918392658233643},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.107.4380","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.107.4380","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.tecn.upf.es/~jonsson/nips01.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.25.8077","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.25.8077","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-anw.cs.umass.edu/papers/2000/JonssonBartoUTree2001.ps.gz","raw_type":"text"},{"id":"pmh:oai:scholarworks.umass.edu:cs_faculty_pubs-1345","doi":null,"is_oa":false,"landing_page_url":"https://scholarworks.umass.edu/cs_faculty_pubs/346","pdf_url":null,"source":{"id":"https://openalex.org/S4306402240","display_name":"ScholarWorks@UMassAmherst (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Computer Science Department Faculty Publication Series","raw_type":"text"},{"id":"pmh:oai:scholarworks.umass.edu:20.500.14394/10011","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/20.500.14394/10011","pdf_url":null,"source":{"id":"https://openalex.org/S4306402057","display_name":"Scholarworks (University of Massachusetts Amherst)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I24603500","host_organization_name":"University of Massachusetts Amherst","host_organization_lineage":["https://openalex.org/I24603500"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"published","raw_type":"Article"},{"id":"mag:2107628283","doi":null,"is_oa":false,"landing_page_url":"http://papers.nips.cc/paper/1821-automated-state-abstraction-for-options-using-the-u-tree-algorithm.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W16046748","https://openalex.org/W1488771041","https://openalex.org/W1494114146","https://openalex.org/W1583380718","https://openalex.org/W1754881896","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2156067405","https://openalex.org/W2158548602","https://openalex.org/W2548352678"],"related_works":["https://openalex.org/W7045527244","https://openalex.org/W7097130758","https://openalex.org/W7095479277","https://openalex.org/W7095343162","https://openalex.org/W7054597619","https://openalex.org/W7099548677","https://openalex.org/W7096597061","https://openalex.org/W7038745379","https://openalex.org/W4253326649","https://openalex.org/W116921725"],"abstract_inverted_index":{"Learning":[0],"a":[1,10,100],"complex":[2],"task":[3],"can":[4,16],"be":[5,76],"significantly":[6],"facilitated":[7],"by":[8],"defining":[9],"hierarchy":[11],"of":[12,45,54,88,128],"subtasks.":[13],"An":[14],"agent":[15],"learn":[17],"to":[18,30,50,68,70,83,115],"choose":[19],"between":[20],"various":[21],"temporally":[22,137],"abstract":[23],"actions,":[24],"each":[25],"solving":[26],"an":[27,112],"assigned":[28],"subtask,":[29],"accomplish":[31],"the":[32,43,89,96,126],"overall":[33],"task.":[34,103],"In":[35],"this":[36,66],"paper,":[37],"we":[38,94],"study":[39],"hierarchical":[40,55,102,117],"learning":[41,118,130],"using":[42,99],"framework":[44],"options.":[46],"We":[47,78],"argue":[48],"that":[49,64,106],"take":[51],"full":[52],"advantage":[53],"structure,":[56],"one":[57],"should":[58,75],"perform":[59],"option-specific":[60,86,108],"state":[61,73,90,109],"abstraction,":[62],"and":[63,93],"if":[65],"is":[67,111],"scale":[69],"larger":[71],"tasks,":[72],"abstraction":[74,110],"automated.":[77],"adapt":[79],"McCallum's":[80],"U-Tree":[81],"algorithm":[82,98],"automatically":[84],"build":[85],"representations":[87],"feature":[91],"space,":[92],"illustrate":[95],"resulting":[97],"simple":[101],"Results":[104],"suggest":[105],"automated":[107],"attractive":[113],"approach":[114],"making":[116],"systems":[119],"more":[120],"effective.":[121],"1":[122],"Introduction":[123],"Researchers":[124],"in":[125],"field":[127],"reinforcement":[129],"have":[131],"recently":[132],"focused":[133],"considerable":[134],"attention":[135],"on":[136],"abst...":[138]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}