{"id":"https://openalex.org/W3010145806","doi":"https://doi.org/10.1109/icra40945.2020.9197020","title":"Scalable Multi-Task Imitation Learning with Autonomous Improvement","display_name":"Scalable Multi-Task Imitation Learning with Autonomous Improvement","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3010145806","doi":"https://doi.org/10.1109/icra40945.2020.9197020","mag":"3010145806"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2003.02636","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071640510","display_name":"Avi Singh","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"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Avi Singh","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083516691","display_name":"Eric Jang","orcid":null},"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":"Eric Jang","raw_affiliation_strings":["Robotics at Google"],"affiliations":[{"raw_affiliation_string":"Robotics at Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067856495","display_name":"Alexander Irpan","orcid":null},"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":"Alexander Irpan","raw_affiliation_strings":["Robotics at Google"],"affiliations":[{"raw_affiliation_string":"Robotics at Google","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039293409","display_name":"Daniel Kappler","orcid":null},"institutions":[{"id":"https://openalex.org/I2802050120","display_name":"Southern General Hospital","ror":"https://ror.org/04wvkky61","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2800201399","https://openalex.org/I2802050120"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel Kappler","raw_affiliation_strings":["X"],"affiliations":[{"raw_affiliation_string":"X","institution_ids":["https://openalex.org/I2802050120"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060660082","display_name":"Murtaza Dalal","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"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":"Murtaza Dalal","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levinev","raw_affiliation_strings":["UC Berkeley"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065802887","display_name":"Mohi Khansari","orcid":null},"institutions":[{"id":"https://openalex.org/I2802050120","display_name":"Southern General Hospital","ror":"https://ror.org/04wvkky61","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I2800201399","https://openalex.org/I2802050120"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mohi Khansari","raw_affiliation_strings":["X"],"affiliations":[{"raw_affiliation_string":"X","institution_ids":["https://openalex.org/I2802050120"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874"},"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":"Chelsea Finn","raw_affiliation_strings":["Robotics at Google"],"affiliations":[{"raw_affiliation_string":"Robotics at Google","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5071640510"],"corresponding_institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.58743819,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71568183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2167","last_page":"2173"},"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":0.9990000128746033,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9969000220298767,"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":0.7565931081771851},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6990012526512146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6933654546737671},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6907141208648682},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6259051561355591},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5923928022384644},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5640501976013184},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5337287783622742},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5111752152442932},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.43369007110595703},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4294655919075012},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3912214934825897},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.21534347534179688},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09106260538101196}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7565931081771851},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6990012526512146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6933654546737671},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6907141208648682},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6259051561355591},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5923928022384644},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5640501976013184},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5337287783622742},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5111752152442932},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.43369007110595703},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4294655919075012},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3912214934825897},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.21534347534179688},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09106260538101196},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra40945.2020.9197020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2003.02636","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.02636","pdf_url":"https://arxiv.org/pdf/2003.02636","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3010145806","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2003.02636.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2003.02636","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2003.02636","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2003.02636","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2003.02636","pdf_url":"https://arxiv.org/pdf/2003.02636","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3010145806.pdf","grobid_xml":"https://content.openalex.org/works/W3010145806.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1594201624","https://openalex.org/W1757796397","https://openalex.org/W1929981607","https://openalex.org/W1969074599","https://openalex.org/W1999874108","https://openalex.org/W2061562262","https://openalex.org/W2121863487","https://openalex.org/W2130726249","https://openalex.org/W2138621090","https://openalex.org/W2142641780","https://openalex.org/W2167224731","https://openalex.org/W2169498096","https://openalex.org/W2594640072","https://openalex.org/W2754517384","https://openalex.org/W2785342287","https://openalex.org/W2815036811","https://openalex.org/W2896924405","https://openalex.org/W2904246096","https://openalex.org/W2914584948","https://openalex.org/W2938421504","https://openalex.org/W2942608247","https://openalex.org/W2951262671","https://openalex.org/W2962722175","https://openalex.org/W2962732055","https://openalex.org/W2963003097","https://openalex.org/W2963094133","https://openalex.org/W2963120839","https://openalex.org/W2963277051","https://openalex.org/W2963484919","https://openalex.org/W2963590100","https://openalex.org/W2963669336","https://openalex.org/W2963703448","https://openalex.org/W2964001908","https://openalex.org/W2964121744","https://openalex.org/W2964157221","https://openalex.org/W2965916140","https://openalex.org/W2966564143","https://openalex.org/W4211089519","https://openalex.org/W6631190155","https://openalex.org/W6635701881","https://openalex.org/W6637967152","https://openalex.org/W6640443443","https://openalex.org/W6684338915","https://openalex.org/W6696380822","https://openalex.org/W6718092244","https://openalex.org/W6731982132","https://openalex.org/W6734205138","https://openalex.org/W6735944222","https://openalex.org/W6740801417","https://openalex.org/W6741798502","https://openalex.org/W6744181227","https://openalex.org/W6744925309","https://openalex.org/W6745747580","https://openalex.org/W6748566876","https://openalex.org/W6753049910","https://openalex.org/W6754628760","https://openalex.org/W6757592117","https://openalex.org/W6763103943","https://openalex.org/W6842914433"],"related_works":["https://openalex.org/W3091086138","https://openalex.org/W3170104202","https://openalex.org/W3132095429","https://openalex.org/W2962732055","https://openalex.org/W2951262671","https://openalex.org/W3172303261","https://openalex.org/W846029135","https://openalex.org/W3199185513","https://openalex.org/W3009295642","https://openalex.org/W3206093119","https://openalex.org/W2120982521","https://openalex.org/W1991618009","https://openalex.org/W3204607681","https://openalex.org/W2767661932","https://openalex.org/W2996086858","https://openalex.org/W2991408422","https://openalex.org/W2898525034","https://openalex.org/W2209580443","https://openalex.org/W3206200647","https://openalex.org/W3197318324"],"abstract_inverted_index":{"While":[0],"robot":[1,29,46,156,168,218],"learning":[2,69,231,250],"has":[3,38],"demonstrated":[4],"promising":[5],"results":[6],"for":[7,27,45,54,148,242],"enabling":[8,216],"robots":[9],"to":[10,30,65,88,140,210,219,223,228,248],"automatically":[11],"acquire":[12],"new":[13,224],"skills,":[14],"a":[15,40,111,120,123,131,178,197],"critical":[16],"challenge":[17],"in":[18,36,119,246],"deploying":[19],"learning-based":[20],"systems":[21],"is":[22],"scale:":[23],"acquiring":[24],"enough":[25],"data":[26,55,77,238],"the":[28,82,90,103,116,142,152,155,167,183,194,206,217],"effectively":[31,255],"generalize":[32],"broadly.":[33],"Imitation":[34],"learning,":[35,47,87],"particular,":[37],"remained":[39],"stable":[41],"and":[42,93,245],"powerful":[43],"approach":[44],"but":[48],"critically":[49],"relies":[50],"on":[51],"expert":[52],"operators":[53],"collection.":[56],"In":[57,226],"this":[58,62],"work,":[59],"we":[60,101],"target":[61],"challenge,":[63],"aiming":[64],"build":[66],"an":[67,160],"imitation":[68,106,230],"system":[70],"that":[71,154],"can":[72,235,254],"continuously":[73],"improve":[74,256],"through":[75],"autonomous":[76,108],"collection,":[78],"while":[79],"simultaneously":[80],"avoiding":[81],"explicit":[83],"use":[84],"of":[85,95,105,163,181,201],"reinforcement":[86,249],"maintain":[89],"stability,":[91],"simplicity,":[92],"scalability":[94],"supervised":[96],"imitation.":[97],"To":[98],"accomplish":[99],"this,":[100],"cast":[102],"problem":[104],"with":[107,177,239],"improvement":[109],"into":[110,196],"multi-task":[112,121,164],"setting.":[113],"We":[114,191],"utilize":[115],"insight":[117],"that,":[118],"setting,":[122],"failed":[124],"attempt":[125,133],"at":[126,134],"one":[127,153],"task":[128,188],"might":[129],"represent":[130],"successful":[132],"another":[135],"task.":[136],"This":[137],"allows":[138],"us":[139],"leverage":[141],"robot's":[143],"own":[144],"trials":[145,171,195],"as":[146],"demonstrations":[147],"tasks":[149],"other":[150],"than":[151],"actually":[157],"attempted.":[158],"Using":[159],"initial":[161,207],"dataset":[162],"demonstration":[165,208],"data,":[166],"autonomously":[169,236],"collects":[170],"which":[172],"are":[173],"only":[174,205],"sparsely":[175],"labeled":[176],"binary":[179],"indication":[180],"whether":[182],"trial":[184],"accomplished":[185],"any":[186],"useful":[187],"or":[189],"not.":[190],"then":[192],"embed":[193],"learned":[198],"latent":[199],"space":[200],"tasks,":[202],"trained":[203],"using":[204],"dataset,":[209],"draw":[211],"similarities":[212],"between":[213],"various":[214],"trials,":[215],"achieve":[220],"one-shot":[221],"generalization":[222],"tasks.":[225],"contrast":[227,247],"prior":[229],"approaches,":[232],"our":[233,252],"method":[234,253],"collect":[237],"sparse":[240],"supervision":[241],"continuous":[243],"improvement,":[244],"algorithms,":[251],"from":[257],"sparse,":[258],"task-agnostic":[259],"reward":[260],"signals.":[261]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}