{"id":"https://openalex.org/W2980766741","doi":"https://doi.org/10.1177/0278364920944474","title":"Scaling simulation-to-real transfer by learning a latent space of robot skills","display_name":"Scaling simulation-to-real transfer by learning a latent space of robot skills","publication_year":2020,"publication_date":"2020-08-21","ids":{"openalex":"https://openalex.org/W2980766741","doi":"https://doi.org/10.1177/0278364920944474","mag":"2980766741"},"language":"en","primary_location":{"id":"doi:10.1177/0278364920944474","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364920944474","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","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/A5041959064","display_name":"Ryan Julian","orcid":null},"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":true,"raw_author_name":"Ryan C Julian","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073253090","display_name":"Eric Heiden","orcid":"https://orcid.org/0000-0002-2031-8564"},"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":"Eric Heiden","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103934489","display_name":"Zhanpeng He","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhanpeng He","raw_affiliation_strings":["Columbia University, New York, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047725424","display_name":"Hejia Zhang","orcid":"https://orcid.org/0000-0001-5222-5277"},"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":"Hejia Zhang","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029642293","display_name":"Stefan Schaal","orcid":"https://orcid.org/0000-0001-5660-1874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stefan Schaal","raw_affiliation_strings":["X, Mountain View, CA USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X, Mountain View, CA USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110492675","display_name":"Joseph J. Lim","orcid":null},"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":"Joseph J Lim","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077367921","display_name":"Gaurav S. Sukhatme","orcid":"https://orcid.org/0000-0003-2408-474X"},"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":"Gaurav S Sukhatme","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088777896","display_name":"Karol Hausman","orcid":"https://orcid.org/0000-0002-1504-6197"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karol Hausman","raw_affiliation_strings":["Google Brain, Robotics at Google Team, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain, Robotics at Google Team, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5041959064"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.2608,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.60977338,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"39","issue":"10-11","first_page":"1259","last_page":"1278"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9990000128746033,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.979200005531311,"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/computer-science","display_name":"Computer science","score":0.644588053226471},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5731590986251831},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5685741901397705},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5088327527046204},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48378464579582214},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.465951532125473},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43756720423698425},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.41017404198646545},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11963501572608948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.644588053226471},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5731590986251831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5685741901397705},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5088327527046204},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48378464579582214},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.465951532125473},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43756720423698425},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.41017404198646545},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11963501572608948},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0278364920944474","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0278364920944474","pdf_url":null,"source":{"id":"https://openalex.org/S73484101","display_name":"The International Journal of Robotics Research","issn_l":"0278-3649","issn":["0278-3649","1741-3176"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of Robotics Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G1512921589","display_name":null,"funder_award_id":"IIS-1205249","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4227778692","display_name":null,"funder_award_id":"EECS-0926052","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6115495753","display_name":null,"funder_award_id":"IIS-1017134","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322434","display_name":"Max-Planck-Gesellschaft","ror":"https://ror.org/01hhn8329"},{"id":"https://openalex.org/F4320322617","display_name":"Okawa Foundation for Information and Telecommunications","ror":"https://ror.org/01enbtr31"},{"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":21,"referenced_works":["https://openalex.org/W1513084430","https://openalex.org/W1522356730","https://openalex.org/W1583837637","https://openalex.org/W1923344279","https://openalex.org/W2015900931","https://openalex.org/W2069361969","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2575705757","https://openalex.org/W2612690371","https://openalex.org/W2623293810","https://openalex.org/W2767050701","https://openalex.org/W2962736495","https://openalex.org/W2962957005","https://openalex.org/W2963614114","https://openalex.org/W2964161785","https://openalex.org/W2974036678","https://openalex.org/W2999905431","https://openalex.org/W3101442004","https://openalex.org/W3110471395","https://openalex.org/W4231832368"],"related_works":["https://openalex.org/W2770593030","https://openalex.org/W4281727072","https://openalex.org/W2560201613","https://openalex.org/W3154990682","https://openalex.org/W2171975302","https://openalex.org/W2022352247","https://openalex.org/W1532073221","https://openalex.org/W2377538627","https://openalex.org/W2110944602","https://openalex.org/W3213722473"],"abstract_inverted_index":{"We":[0,76,126],"present":[1],"a":[2,26,48,58,72,87,190,242,256],"strategy":[3],"for":[4,28,51,121,246,259],"simulation-to-real":[5,37],"transfer,":[6],"which":[7,39,90,131,173],"builds":[8],"on":[9,19,230],"recent":[10],"advances":[11],"in":[12,71,82,141,180,193],"robot":[13,192],"skill":[14,69,114,175],"decomposition.":[15],"Rather":[16],"than":[17],"focusing":[18],"minimizing":[20],"the":[21,30,109,162,181,207,210,224],"simulation\u2013reality":[22],"gap,":[23],"we":[24,56,106,250],"propose":[25],"method":[27,134,186,254],"increasing":[29],"sample":[31,244],"efficiency":[32],"and":[33,42,63,66,80,100,169,222],"robustness":[34],"of":[35,46,61,111,233,248],"existing":[36],"approaches":[38],"exploits":[40],"hierarchy":[41],"online":[43,155],"adaptation.":[44],"Instead":[45],"learning":[47],"unique":[49],"policy":[50,89],"each":[52],"desired":[53],"robotic":[54],"task,":[55],"learn":[57],"diverse":[59],"set":[60],"skills":[62,99,160,226],"their":[64,101],"variations,":[65],"embed":[67],"those":[68],"variations":[70],"continuously":[73],"parameterized":[74],"space.":[75],"then":[77,127],"interpolate,":[78],"search,":[79],"plan":[81],"this":[83,104,112],"space":[84],"to":[85,135,152,171,188,195,220,238],"find":[86],"transferable":[88,217],"solves":[91],"more":[92],"complex,":[93],"high-level":[94,198,234],"tasks":[95,138,154,199],"by":[96,116,143,156],"combining":[97,260],"low-level":[98,211,225],"variations.":[102],"In":[103,236],"work,":[105],"first":[107],"characterize":[108],"behavior":[110],"learned":[113],"space,":[115,164],"experimenting":[117],"with":[118,200,263],"several":[119],"techniques":[120],"composing":[122],"pre-learned":[123],"latent":[124,147,163,174],"skills.":[125,148],"discuss":[128],"an":[129],"algorithm":[130,150],"allows":[132],"our":[133,185,239,253],"perform":[136,177],"long-horizon":[137],"never":[139],"seen":[140],"simulation,":[142],"intelligently":[144],"sequencing":[145],"short-horizon":[146],"Our":[149],"adapts":[151],"unseen":[153],"repeatedly":[157],"choosing":[158],"new":[159],"from":[161,218],"using":[165],"live":[166],"sensor":[167],"data":[168],"simulation":[170,219],"predict":[172],"will":[176],"best":[178],"next":[179],"real":[182,191],"world.":[183],"Importantly,":[184],"learns":[187],"control":[189],"joint-space":[194],"achieve":[196],"these":[197],"little":[201],"or":[202],"no":[203],"on-robot":[204],"time,":[205],"despite":[206],"fact":[208],"that":[209,223,252],"policies":[212],"may":[213],"not":[214,228],"be":[215],"perfectly":[216],"real,":[221],"were":[227],"trained":[229],"any":[231],"examples":[232],"tasks.":[235],"addition":[237],"results":[240],"indicating":[241],"lower":[243],"complexity":[245],"families":[247],"tasks,":[249],"believe":[251],"provides":[255],"promising":[257],"template":[258],"learning-based":[261],"methods":[262],"proven":[264],"classical":[265],"robotics":[266],"algorithms":[267],"such":[268],"as":[269],"model-predictive":[270],"control.":[271]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
