{"id":"https://openalex.org/W2071444114","doi":"https://doi.org/10.1109/humanoids.2011.6100841","title":"Hierarchical reinforcement learning with movement primitives","display_name":"Hierarchical reinforcement learning with movement primitives","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2071444114","doi":"https://doi.org/10.1109/humanoids.2011.6100841","mag":"2071444114"},"language":"en","primary_location":{"id":"doi:10.1109/humanoids.2011.6100841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2011.6100841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 11th IEEE-RAS International Conference on Humanoid Robots","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/A5017689065","display_name":"Freek Stulp","orcid":"https://orcid.org/0000-0001-9555-9517"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Freek Stulp","raw_affiliation_strings":["Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA","Computational Learning and Motor Control Lab, University of Southern California, Los Angeles, 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Computational Learning and Motor Control Lab, University of Southern California, Los Angeles, 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029642293","display_name":"Stefan Schaal","orcid":"https://orcid.org/0000-0001-5660-1874"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Schaal","raw_affiliation_strings":["Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA","Computational Learning and Motor Control Lab, University of Southern California, Los Angeles, 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Laboratory, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Computational Learning and Motor Control Lab, University of Southern California, Los Angeles, 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":77,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"231","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9980999827384949,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9638000130653381,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8069685101509094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7720128893852234},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.688416063785553},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.593473494052887},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5816556215286255},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5712469816207886},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5659756660461426},{"id":"https://openalex.org/keywords/movement","display_name":"Movement (music)","score":0.5268070697784424},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5263770222663879},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.516035795211792},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.47598257660865784},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4680107831954956},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45726877450942993}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8069685101509094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720128893852234},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.688416063785553},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.593473494052887},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5816556215286255},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5712469816207886},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5659756660461426},{"id":"https://openalex.org/C2780226923","wikidata":"https://www.wikidata.org/wiki/Q929848","display_name":"Movement (music)","level":2,"score":0.5268070697784424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5263770222663879},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.516035795211792},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47598257660865784},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4680107831954956},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45726877450942993},{"id":"https://openalex.org/C107038049","wikidata":"https://www.wikidata.org/wiki/Q35986","display_name":"Aesthetics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","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":4,"locations":[{"id":"doi:10.1109/humanoids.2011.6100841","is_oa":false,"landing_page_url":"https://doi.org/10.1109/humanoids.2011.6100841","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 11th IEEE-RAS International Conference on Humanoid Robots","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.395.9269","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.395.9269","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ensta-paristech.fr/~stulp/publications/pdfs/stulp11hierarchical.pdf","raw_type":"text"},{"id":"pmh:oai:edoc.mpg.de:590905","is_oa":false,"landing_page_url":"http://edoc.mpg.de/590905","pdf_url":null,"source":{"id":"https://openalex.org/S4406922265","display_name":"Max Planck Institute for Plasma Physics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"11th IEEE-RAS International Conference on Humanoid Robots (Humanoids) 2011, IEEE, 231-238 (2011)","raw_type":"Conference-Paper"},{"id":"pmh:oai:pure.mpg.de:item_1577795","is_oa":false,"landing_page_url":"http://hdl.handle.net/11858/00-001M-0000-0010-4EE1-C","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2011 11th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2011)","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.7300000190734863}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1502364872","https://openalex.org/W1556151214","https://openalex.org/W1592847719","https://openalex.org/W1925816294","https://openalex.org/W1982803779","https://openalex.org/W2105546430","https://openalex.org/W2105777811","https://openalex.org/W2107767097","https://openalex.org/W2110304639","https://openalex.org/W2113698995","https://openalex.org/W2116226448","https://openalex.org/W2120772693","https://openalex.org/W2121518244","https://openalex.org/W2147828974","https://openalex.org/W2151975555","https://openalex.org/W2167647761","https://openalex.org/W6676348739","https://openalex.org/W6676403623"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W2364921833","https://openalex.org/W2302028273","https://openalex.org/W1525643724","https://openalex.org/W4294811414","https://openalex.org/W4285805438","https://openalex.org/W4313123734","https://openalex.org/W2068265187","https://openalex.org/W2574848952","https://openalex.org/W4238175311"],"abstract_inverted_index":{"Temporal":[0],"abstraction":[1],"and":[2,12,14,77,115,143,145],"task":[3,151],"decomposition":[4],"drastically":[5],"reduce":[6],"the":[7,25,35,83,105,109,113,116,123,127,130,154],"search":[8],"space":[9],"for":[10],"planning":[11],"control,":[13],"are":[15,32,87],"fundamental":[16],"to":[17,22,56,108,126],"making":[18],"complex":[19],"tasks":[20],"amenable":[21],"learning.":[23,40],"In":[24],"context":[26],"of":[27,37,58,75,82,93,98,129],"reinforcement":[28,39,45],"learning,":[29],"temporal":[30,94],"abstractions":[31],"studied":[33],"within":[34],"paradigm":[36],"hierarchical":[38,44],"We":[41,135],"propose":[42],"a":[43,99,149,163],"learning":[46],"approach":[47,138],"by":[48],"applying":[49],"our":[50,137],"algorithm":[51],"PI":[52],"<sup":[53],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[54],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[55],"sequences":[57],"Dynamic":[59,84],"Movement":[60,85],"Primitives.":[61],"For":[62],"robots,":[63],"this":[64],"representation":[65],"has":[66],"some":[67],"important":[68],"advantages":[69],"over":[70],"discrete":[71],"representations":[72],"in":[73,112,148,152,162],"terms":[74],"scalability":[76],"convergence":[78],"speed.":[79],"The":[80,96],"parameters":[81],"Primitives":[86],"learned":[88],"simultaneously":[89],"at":[90],"different":[91,160],"levels":[92],"abstraction.":[95],"shape":[97],"movement":[100,120,132],"primitive":[101,111,133],"is":[102],"optimized":[103],"w.r.t.":[104,122],"costs":[106,124],"up":[107,125],"next":[110],"sequence,":[114],"subgoals":[117],"between":[118,159],"two":[119],"primitives":[121],"end":[128],"entire":[131],"sequence.":[134],"implement":[136],"on":[139],"an":[140,157],"11-DOF":[141],"arm":[142],"hand,":[144],"evaluate":[146],"it":[147],"pick-and-place":[150],"which":[153],"robot":[155],"transports":[156],"object":[158],"shelves":[161],"cupboard.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
