{"id":"https://openalex.org/W2126909264","doi":"https://doi.org/10.1109/icra.2015.7138994","title":"Learning contact-rich manipulation skills with guided policy search","display_name":"Learning contact-rich manipulation skills with guided policy search","publication_year":2015,"publication_date":"2015-05-01","ids":{"openalex":"https://openalex.org/W2126909264","doi":"https://doi.org/10.1109/icra.2015.7138994","mag":"2126909264"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2015.7138994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2015.7138994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010914575","display_name":"Nolan Wagener","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nolan Wagener","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of California, Berkeley, 94709, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026322200"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":28.6048,"has_fulltext":false,"cited_by_count":280,"citation_normalized_percentile":{"value":0.99736955,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"156","last_page":"163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9933000206947327,"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/computer-science","display_name":"Computer science","score":0.7370738983154297},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.631168782711029},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6240266561508179},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5818793177604675},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5767843127250671},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.575146496295929},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5647847652435303},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5186892747879028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5146158933639526},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.49226847290992737},{"id":"https://openalex.org/keywords/motion-control","display_name":"Motion control","score":0.4325534999370575},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.42068374156951904},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3312433362007141}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7370738983154297},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.631168782711029},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6240266561508179},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5818793177604675},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5767843127250671},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.575146496295929},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5647847652435303},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5186892747879028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5146158933639526},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.49226847290992737},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.4325534999370575},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.42068374156951904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3312433362007141},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2015.7138994","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2015.7138994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1520597402","https://openalex.org/W1564755532","https://openalex.org/W1813260711","https://openalex.org/W1931877416","https://openalex.org/W1977655452","https://openalex.org/W2001095967","https://openalex.org/W2012587148","https://openalex.org/W2027457629","https://openalex.org/W2041242313","https://openalex.org/W2042882799","https://openalex.org/W2051620263","https://openalex.org/W2098284983","https://openalex.org/W2100235553","https://openalex.org/W2104733512","https://openalex.org/W2109008048","https://openalex.org/W2121103318","https://openalex.org/W2123967136","https://openalex.org/W2125612430","https://openalex.org/W2129515556","https://openalex.org/W2131119817","https://openalex.org/W2139053308","https://openalex.org/W2147032798","https://openalex.org/W2156377376","https://openalex.org/W2161395589","https://openalex.org/W2168945912","https://openalex.org/W2172158418","https://openalex.org/W2295431040","https://openalex.org/W2296319761","https://openalex.org/W2554830522","https://openalex.org/W2591436094","https://openalex.org/W2962957031","https://openalex.org/W4205513846","https://openalex.org/W4237733001","https://openalex.org/W4250589301","https://openalex.org/W6631149375","https://openalex.org/W6633472939","https://openalex.org/W6638443265","https://openalex.org/W6640174482","https://openalex.org/W6674909112","https://openalex.org/W6675999342","https://openalex.org/W6678157427","https://openalex.org/W6678367057","https://openalex.org/W6681631837","https://openalex.org/W6682093400","https://openalex.org/W6683180588","https://openalex.org/W7073827480"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W4381094582","https://openalex.org/W1978893398","https://openalex.org/W1977906818","https://openalex.org/W2201908702","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W2044900919"],"abstract_inverted_index":{"Autonomous":[0],"learning":[1,30],"of":[2,19,65,86,152],"object":[3],"manipulation":[4,67],"skills":[5],"can":[6,111,144,156],"enable":[7,117],"robots":[8],"to":[9,16,36,61,113,120],"acquire":[10,145],"rich":[11],"behavioral":[12],"repertoires":[13],"that":[14,110,130,141],"scale":[15],"the":[17,23,34,89,132],"variety":[18],"objects":[20],"found":[21],"in":[22],"real":[24,124],"world.":[25],"However,":[26],"current":[27],"motion":[28,91],"skill":[29,92],"methods":[31],"typically":[32],"restrict":[33],"behavior":[35],"a":[37,51,63,84,106,123,166,180,184],"compact,":[38],"low-dimensional":[39],"representation,":[40],"limiting":[41],"its":[42],"expressiveness":[43],"and":[44,58,100,135,155,186],"generality.":[45],"In":[46],"this":[47,118],"paper,":[48],"we":[49,126],"extend":[50],"recently":[52],"developed":[53],"policy":[54,72,109],"search":[55],"method":[56,119,143],"[1]":[57],"use":[59],"it":[60],"learn":[62,157],"range":[64],"dynamic":[66],"behaviors":[68,148],"with":[69],"highly":[70],"general":[71],"representations,":[73],"without":[74],"using":[75,94],"known":[76],"models":[77],"or":[78],"example":[79],"demonstrations.":[80],"Our":[81],"approach":[82],"learns":[83],"set":[85],"trajectories":[87,104],"for":[88,160],"desired":[90],"by":[93],"iteratively":[95],"refitted":[96],"time-varying":[97],"linear":[98],"models,":[99],"then":[101],"unifies":[102],"these":[103],"into":[105,183],"single":[107],"control":[108],"generalize":[112],"new":[114],"situations.":[115],"To":[116],"run":[121],"on":[122],"robot,":[125],"introduce":[127],"several":[128],"improvements":[129],"reduce":[131],"sample":[133],"count":[134],"automate":[136],"parameter":[137],"selection.":[138],"We":[139],"show":[140],"our":[142],"fast,":[146],"fluent":[147],"after":[149],"only":[150],"minutes":[151],"interaction":[153],"time,":[154],"robust":[158],"controllers":[159],"complex":[161],"tasks,":[162],"including":[163],"putting":[164],"together":[165],"toy":[167],"airplane,":[168],"stacking":[169],"tight-fitting":[170,177],"lego":[171],"blocks,":[172],"placing":[173],"wooden":[174],"rings":[175],"onto":[176,190],"pegs,":[178],"inserting":[179],"shoe":[181],"tree":[182],"shoe,":[185],"screwing":[187],"bottle":[188],"caps":[189],"bottles.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":41},{"year":2020,"cited_by_count":42},{"year":2019,"cited_by_count":49},{"year":2018,"cited_by_count":29},{"year":2017,"cited_by_count":28},{"year":2016,"cited_by_count":19},{"year":2015,"cited_by_count":8}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}