{"id":"https://openalex.org/W1987540542","doi":"https://doi.org/10.1109/devlrn.2010.5578832","title":"Imitation learning with hierarchical actions","display_name":"Imitation learning with hierarchical actions","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W1987540542","doi":"https://doi.org/10.1109/devlrn.2010.5578832","mag":"1987540542"},"language":"en","primary_location":{"id":"doi:10.1109/devlrn.2010.5578832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2010.5578832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 9th International Conference on Development and Learning","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5077191191","display_name":"Abram L. Friesen","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abram L. Friesen","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Washington, Seattle, WA, USA","Dept. of Computer Science and Engineering, University of Washington, Seattle, WA, 98195, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Dept. of Computer Science and Engineering, University of Washington, Seattle, WA, 98195, USA#TAB#","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002759219","display_name":"Rajesh P. N. Rao","orcid":"https://orcid.org/0000-0003-0682-8952"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajesh P. N. Rao","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Washington, Seattle, WA, USA","Dept. of Computer Science and Engineering, University of Washington, Seattle, WA, 98195, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Dept. of Computer Science and Engineering, University of Washington, Seattle, WA, 98195, USA#TAB#","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":0.2725,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.47600422,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2371","issue":null,"first_page":"263","last_page":"268"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/imitation","display_name":"Imitation","score":0.7489438056945801},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7013636231422424},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6808124780654907},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5505349040031433},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5356898307800293},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5324885249137878},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5294620394706726},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5206053256988525},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3654389977455139},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1910899579524994}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7489438056945801},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7013636231422424},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6808124780654907},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5505349040031433},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5356898307800293},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5324885249137878},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5294620394706726},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5206053256988525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3654389977455139},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1910899579524994},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/devlrn.2010.5578832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/devlrn.2010.5578832","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 9th International Conference on Development and Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W143632683","https://openalex.org/W195812645","https://openalex.org/W196386631","https://openalex.org/W1486707268","https://openalex.org/W1490071011","https://openalex.org/W1556824961","https://openalex.org/W1585013689","https://openalex.org/W1592441824","https://openalex.org/W1592847719","https://openalex.org/W1594602740","https://openalex.org/W1999874108","https://openalex.org/W2043615441","https://openalex.org/W2075670547","https://openalex.org/W2097668489","https://openalex.org/W2101448784","https://openalex.org/W2103254706","https://openalex.org/W2109910161","https://openalex.org/W2117778675","https://openalex.org/W2120591602","https://openalex.org/W2121863487","https://openalex.org/W2131960487","https://openalex.org/W2133695754","https://openalex.org/W2139612737","https://openalex.org/W2159231499","https://openalex.org/W2166302491","https://openalex.org/W2560731476","https://openalex.org/W4214717370","https://openalex.org/W4249441547","https://openalex.org/W4253823376","https://openalex.org/W6605823206","https://openalex.org/W6607902129","https://openalex.org/W6607933126","https://openalex.org/W6628902087","https://openalex.org/W6635524107","https://openalex.org/W6674687248","https://openalex.org/W6680292960"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2202218907"],"abstract_inverted_index":{"Imitation":[0],"is":[1,117],"a":[2,13,27,44,62,111,120,144,157,182],"powerful":[3],"mechanism":[4],"for":[5,65,72,128],"rapidly":[6,140],"learning":[7,74,82,180],"new":[8,63,76],"skills":[9],"through":[10],"observation":[11],"of":[12,46,52,54,75,88,147],"mentor.":[14],"Developmental":[15],"studies":[16,127],"indicate":[17],"that":[18,68,102,116,136,164],"children":[19],"often":[20],"perform":[21],"goal-based":[22,66],"imitation":[23,67,131,166],"rather":[24],"than":[25],"mimicking":[26],"mentor's":[28],"actual":[29],"action":[30,70,187],"trajectories.":[31],"Further,":[32],"imitation,":[33,81],"and":[34],"human":[35,80],"behavior":[36],"in":[37,79,125,132,171,174],"general,":[38],"appear":[39],"to":[40,142,150,155,179],"be":[41,105],"based":[42],"on":[43,85],"hierarchy":[45],"actions,":[47],"with":[48],"higher-level":[49],"actions":[50,104,149],"composed":[51],"sequences":[53],"lower-level":[55],"actions.":[56],"In":[57],"this":[58],"paper,":[59],"we":[60],"propose":[61],"model":[64,98,139],"exploits":[69],"hierarchies":[71],"fast":[73],"skills.":[77],"As":[78],"relies":[83],"only":[84],"sample":[86],"trajectories":[87],"mentor":[89,103,183],"states.":[90],"Unlike":[91],"apprenticeship":[92],"or":[93,184],"inverse":[94],"reinforcement":[95],"learning,":[96,172],"the":[97,137,152],"does":[99],"not":[100],"require":[101],"given.":[106],"We":[107,134],"present":[108],"results":[109,162],"from":[110],"large-scale":[112],"grid":[113],"world":[114],"task":[115,123],"modeled":[118],"after":[119],"puzzle":[121],"box":[122],"used":[124],"developmental":[126],"investigating":[129],"hierarchical":[130,148,165],"children.":[133],"show":[135],"proposed":[138],"learns":[141],"combine":[143],"given":[145],"set":[146],"achieve":[151],"subgoals":[153],"necessary":[154],"reach":[156],"desired":[158],"goal":[159],"state.":[160],"Our":[161],"demonstrate":[163],"can":[167],"yield":[168],"significant":[169],"speed-up":[170],"especially":[173],"large":[175],"state":[176],"spaces,":[177],"compared":[178],"without":[181,185],"an":[186],"hierarchy.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}