{"id":"https://openalex.org/W3023334751","doi":"https://doi.org/10.1109/iros45743.2020.9340848","title":"Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks","display_name":"Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3023334751","doi":"https://doi.org/10.1109/iros45743.2020.9340848","mag":"3023334751"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9340848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9340848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/2004.14404","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040551418","display_name":"Gerrit Schoettler","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Gerrit Schoettler","raw_affiliation_strings":["Siemens","Siemens;"],"affiliations":[{"raw_affiliation_string":"Siemens","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"Siemens;","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021472921","display_name":"Ashvin Nair","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":"Ashvin Nair","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038472921","display_name":"Juan Aparicio Ojea","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Juan Aparicio Ojea","raw_affiliation_strings":["Siemens","Siemens;"],"affiliations":[{"raw_affiliation_string":"Siemens","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"Siemens;","institution_ids":["https://openalex.org/I1325886976"]}]},{"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 Levine","raw_affiliation_strings":["UC Berkeley","UC Berkeley#TAB#"],"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]},{"raw_affiliation_string":"UC Berkeley#TAB#","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043873756","display_name":"Eugen Solowjow","orcid":"https://orcid.org/0000-0001-5222-3706"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Eugen Solowjow","raw_affiliation_strings":["Siemens","Siemens;"],"affiliations":[{"raw_affiliation_string":"Siemens","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"Siemens;","institution_ids":["https://openalex.org/I1325886976"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040551418"],"corresponding_institution_ids":["https://openalex.org/I1325886976"],"apc_list":null,"apc_paid":null,"fwci":0.87928772,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.7331236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"9728","last_page":"9735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991999864578247,"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":0.9771000146865845,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8751558065414429},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6676665544509888},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5992636680603027},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4685410261154175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42748796939849854},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3375207781791687},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16668623685836792}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8751558065414429},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6676665544509888},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5992636680603027},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4685410261154175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42748796939849854},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3375207781791687},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16668623685836792},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros45743.2020.9340848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9340848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2004.14404","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.14404","pdf_url":"https://arxiv.org/pdf/2004.14404","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":"doi:10.48550/arxiv.2004.14404","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2004.14404","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"},{"id":"mag:3023334751","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2004.14404","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2004.14404","pdf_url":"https://arxiv.org/pdf/2004.14404","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":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307782","display_name":"Siemens USA","ror":"https://ror.org/04axb7e79"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3023334751.pdf","grobid_xml":"https://content.openalex.org/works/W3023334751.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1757796397","https://openalex.org/W1938885652","https://openalex.org/W2008731016","https://openalex.org/W2034052310","https://openalex.org/W2064557786","https://openalex.org/W2158782408","https://openalex.org/W2257979135","https://openalex.org/W2421020186","https://openalex.org/W2604763608","https://openalex.org/W2605102758","https://openalex.org/W2607198029","https://openalex.org/W2741122588","https://openalex.org/W2767050701","https://openalex.org/W2781935341","https://openalex.org/W2795756076","https://openalex.org/W2883112541","https://openalex.org/W2905364877","https://openalex.org/W2922881794","https://openalex.org/W2923504512","https://openalex.org/W2962732398","https://openalex.org/W2962902376","https://openalex.org/W2962957005","https://openalex.org/W2963099939","https://openalex.org/W2963165111","https://openalex.org/W2963311874","https://openalex.org/W2963411833","https://openalex.org/W2963544079","https://openalex.org/W2963547174","https://openalex.org/W2963775850","https://openalex.org/W2963906246","https://openalex.org/W2963940579","https://openalex.org/W2964161785","https://openalex.org/W2964198579","https://openalex.org/W2967727187","https://openalex.org/W2968116426","https://openalex.org/W2968217299","https://openalex.org/W2968268581","https://openalex.org/W2981030070","https://openalex.org/W3021593779","https://openalex.org/W3030141984","https://openalex.org/W3101442004","https://openalex.org/W3130717831","https://openalex.org/W6637967152","https://openalex.org/W6666610528","https://openalex.org/W6682849425","https://openalex.org/W6717367658","https://openalex.org/W6731094094","https://openalex.org/W6736057607","https://openalex.org/W6736609842","https://openalex.org/W6741302124","https://openalex.org/W6747473740","https://openalex.org/W6748331328","https://openalex.org/W6750409132","https://openalex.org/W6756848961","https://openalex.org/W6760698134","https://openalex.org/W6760955315","https://openalex.org/W6761443123","https://openalex.org/W6764800732"],"related_works":["https://openalex.org/W3130717831","https://openalex.org/W2890803796","https://openalex.org/W2589275886","https://openalex.org/W3020712699","https://openalex.org/W2964227158","https://openalex.org/W3206200647","https://openalex.org/W3111393852","https://openalex.org/W3087903566","https://openalex.org/W2575705757","https://openalex.org/W3199185513","https://openalex.org/W3165566836","https://openalex.org/W3205641566","https://openalex.org/W3095135648","https://openalex.org/W2968340082","https://openalex.org/W2973019294","https://openalex.org/W2789008106","https://openalex.org/W3138680551","https://openalex.org/W1520597402","https://openalex.org/W3035603778","https://openalex.org/W2518731509"],"abstract_inverted_index":{"Robotic":[0],"insertion":[1,85,109],"tasks":[2,86,110],"are":[3,123],"characterized":[4],"by":[5,78,100],"contact":[6],"and":[7,44,87,120],"friction":[8],"mechanics,":[9],"making":[10],"them":[11],"challenging":[12,107],"for":[13,30],"conventional":[14],"feedback":[15],"control":[16,32],"methods":[17],"due":[18],"to":[19,57,65,69,104],"unmodeled":[20],"physical":[21],"effects.":[22],"Reinforcement":[23],"learning":[24,31,68],"(RL)":[25],"is":[26,55],"a":[27,47,80],"promising":[28],"approach":[29,99],"policies":[33,90],"in":[34,76,92],"such":[35],"settings.":[36],"However,":[37],"RL":[38],"can":[39],"be":[40],"unsafe":[41],"during":[42],"exploration":[43],"might":[45],"require":[46],"large":[48],"amount":[49],"of":[50,73,82,116],"real-world":[51,108,117],"training":[52,101],"data,":[53],"which":[54],"expensive":[56],"collect.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"study":[63],"how":[64],"use":[66],"meta-reinforcement":[67],"solve":[70],"the":[71,74,93],"bulk":[72],"problem":[75],"simulation":[77],"solving":[79],"family":[81],"simulated":[83],"industrial":[84],"then":[88],"adapt":[89],"quickly":[91],"real":[94],"world.":[95],"We":[96],"demonstrate":[97],"our":[98],"an":[102],"agent":[103],"successfully":[105],"perform":[106],"using":[111],"less":[112],"than":[113],"20":[114],"trials":[115],"experience.":[118],"Videos":[119],"other":[121],"material":[122],"available":[124],"at":[125],"https://pearl-insertion.github.io/":[126]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":3}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}