{"id":"https://openalex.org/W2060914855","doi":"https://doi.org/10.1109/tro.2012.2210294","title":"Reinforcement Learning With Sequences of Motion Primitives for Robust Manipulation","display_name":"Reinforcement Learning With Sequences of Motion Primitives for Robust Manipulation","publication_year":2012,"publication_date":"2012-09-05","ids":{"openalex":"https://openalex.org/W2060914855","doi":"https://doi.org/10.1109/tro.2012.2210294","mag":"2060914855"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2012.2210294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2012.2210294","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1546-1904","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"type":"article","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"]},{"id":"https://openalex.org/I201181511","display_name":"\u00c9cole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es","ror":"https://ror.org/0309cs235","country_code":"FR","type":"education","lineage":["https://openalex.org/I201181511","https://openalex.org/I4210145102"]}],"countries":["FR","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","Ecole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es, Paris, France"],"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":"Ecole Nationale Sup\u00e9rieure de Techniques Avanc\u00e9es, Paris, France","institution_ids":["https://openalex.org/I201181511"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044505993","display_name":"Evangelos A. Theodorou","orcid":"https://orcid.org/0000-0002-0834-5738"},"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"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Evangelos A. Theodorou","raw_affiliation_strings":["Computational Learning and Motor Control Laboratory, USC, Seattle, USA","Department of Computer Science and Engineering, University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Laboratory, USC, Seattle, USA","institution_ids":["https://openalex.org/I58610484"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"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/I4210138427","display_name":"Computational Physics (United States)","ror":"https://ror.org/03grsxg62","country_code":"US","type":"company","lineage":["https://openalex.org/I4210138427"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Schaal","raw_affiliation_strings":["Computational Learning and Motor Control Laboratory, USC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Learning and Motor Control Laboratory, USC, USA","institution_ids":["https://openalex.org/I4210138427"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":22.4571,"has_fulltext":false,"cited_by_count":212,"citation_normalized_percentile":{"value":0.99547609,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"28","issue":"6","first_page":"1360","last_page":"1370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9988999962806702,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9988999962806702,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9947999715805054,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.695754885673523},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6330004930496216},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6198726892471313},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6011319756507874},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.585121750831604},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5536617636680603},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.41219091415405273},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.41120994091033936},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3808383345603943},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10008758306503296}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.695754885673523},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6330004930496216},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6198726892471313},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6011319756507874},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.585121750831604},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5536617636680603},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.41219091415405273},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.41120994091033936},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3808383345603943},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10008758306503296},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tro.2012.2210294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tro.2012.2210294","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1546-1904","1941-0468"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1502364872","https://openalex.org/W1517795220","https://openalex.org/W1556151214","https://openalex.org/W1755933627","https://openalex.org/W1925816294","https://openalex.org/W2021446160","https://openalex.org/W2070678636","https://openalex.org/W2076231167","https://openalex.org/W2098524868","https://openalex.org/W2105777811","https://openalex.org/W2109572794","https://openalex.org/W2110304639","https://openalex.org/W2112645080","https://openalex.org/W2113698995","https://openalex.org/W2116226448","https://openalex.org/W2118459920","https://openalex.org/W2121518244","https://openalex.org/W2125549624","https://openalex.org/W2142450096","https://openalex.org/W2142508340","https://openalex.org/W2147828974","https://openalex.org/W2160609165","https://openalex.org/W2169136412","https://openalex.org/W2242447230","https://openalex.org/W2296434941","https://openalex.org/W2591436094","https://openalex.org/W2901136733","https://openalex.org/W3005581722","https://openalex.org/W3020893685","https://openalex.org/W4285719527","https://openalex.org/W6623453879","https://openalex.org/W6640290305","https://openalex.org/W6674872077","https://openalex.org/W6676348739","https://openalex.org/W6756486208"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4323768008","https://openalex.org/W1941703695","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2101105382","https://openalex.org/W2134215012"],"abstract_inverted_index":{"Physical":[0],"contact":[1],"events":[2],"often":[3,63],"allow":[4],"a":[5,26,149],"natural":[6],"decomposition":[7],"of":[8,37,54,77,130,157],"manipulation":[9],"tasks":[10],"into":[11],"action":[12,22],"phases":[13],"and":[14,29,49,75,119,125],"subgoals.":[15],"Within":[16],"the":[17,30,34,52,70,73,78,89,94,97,103,135,155],"motion":[18,27,55,98,131],"primitive":[19],"paradigm,":[20],"each":[21],"phase":[23],"corresponds":[24],"to":[25,33,47,87,115,128,134,147],"primitive,":[28],"subgoals":[31,95],"correspond":[32],"goal":[35,90,120,126],"parameters":[36,53],"these":[38],"primitives.":[39,99],"Current":[40],"state-of-the-art":[41],"reinforcement":[42],"learning":[43,127],"algorithms":[44,62],"are":[45],"able":[46],"efficiently":[48],"robustly":[50],"optimize":[51,88,117],"primitives":[56,132],"in":[57,152],"very":[58],"high-dimensional":[59],"problems.":[60],"These":[61],"consider":[64],"only":[65],"shape":[66,118,124],"parameters,":[67,91],"which":[68,92],"determine":[69],"trajectory":[71],"between":[72,96],"start-":[74],"end-point":[76],"movement.":[79],"In":[80],"manipulation,":[81],"however,":[82],"it":[83],"is":[84],"also":[85],"crucial":[86],"represent":[93],"We":[100,143],"therefore":[101],"extend":[102],"policy":[104],"improvement":[105],"with":[106],"path":[107],"integrals":[108],"(PI":[109],"<sup":[110,139],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[111,140],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[112,141],")":[113],"algorithm":[114,137],"simultaneously":[116],"parameters.":[121],"Applying":[122],"simultaneous":[123],"sequences":[129],"leads":[133],"novel":[136],"PI":[138],"Seq.":[142],"use":[144],"our":[145],"methods":[146],"address":[148],"fundamental":[150],"challenge":[151],"manipulation:":[153],"improving":[154],"robustness":[156],"everyday":[158],"pick-and-place":[159],"tasks.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":28},{"year":2020,"cited_by_count":27},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":8},{"year":2015,"cited_by_count":16},{"year":2014,"cited_by_count":17},{"year":2013,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}