{"id":"https://openalex.org/W2953082648","doi":"https://doi.org/10.1109/iros45743.2020.9341714","title":"Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards","display_name":"Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W2953082648","doi":"https://doi.org/10.1109/iros45743.2020.9341714","mag":"2953082648"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341714","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":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.05841","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":false,"raw_author_name":"Gerrit Schoettler","raw_affiliation_strings":["Siemens Corporation","SIEMENS CORPORATION"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Corporation","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"SIEMENS CORPORATION","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/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":["University of California,Berkeley","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037464692","display_name":"Jianlan Luo","orcid":"https://orcid.org/0009-0008-8029-7794"},"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":"Jianlan Luo","raw_affiliation_strings":["University of California,Berkeley","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090307838","display_name":"Shikhar Bahl","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":"Shikhar Bahl","raw_affiliation_strings":["University of California,Berkeley","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["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 Corporation","SIEMENS CORPORATION"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Corporation","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"SIEMENS CORPORATION","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","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 Corporation","SIEMENS CORPORATION"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Corporation","institution_ids":["https://openalex.org/I1325886976"]},{"raw_affiliation_string":"SIEMENS CORPORATION","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"last","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":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["University of California,Berkeley","University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.0009,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.98415647,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5548","last_page":"5555"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9994000196456909,"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":0.9994000196456909,"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/T10784","display_name":"Muscle activation and electromyography studies","score":0.9896000027656555,"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"}},{"id":"https://openalex.org/T11601","display_name":"Neuroscience and Neural Engineering","score":0.9764999747276306,"subfield":{"id":"https://openalex.org/subfields/2804","display_name":"Cellular and Molecular Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.857789158821106},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767379641532898},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6484593749046326},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5567923784255981},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3930898904800415},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3655575215816498}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.857789158821106},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767379641532898},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6484593749046326},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5567923784255981},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3930898904800415},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3655575215816498}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros45743.2020.9341714","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341714","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:1906.05841","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.05841","pdf_url":"https://arxiv.org/pdf/1906.05841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},{"id":"mag:2953082648","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1906.05841","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.1906.05841","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.05841","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.05841","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.05841","pdf_url":"https://arxiv.org/pdf/1906.05841","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307782","display_name":"Siemens USA","ror":"https://ror.org/04axb7e79"},{"id":"https://openalex.org/F4320322923","display_name":"Siemens","ror":"https://ror.org/059mq0909"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953082648.pdf","grobid_xml":"https://content.openalex.org/works/W2953082648.grobid-xml"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W218896052","https://openalex.org/W1499669280","https://openalex.org/W1520597402","https://openalex.org/W1757796397","https://openalex.org/W1777239053","https://openalex.org/W2098774185","https://openalex.org/W2125612430","https://openalex.org/W2140135625","https://openalex.org/W2155307968","https://openalex.org/W2155968351","https://openalex.org/W2167117957","https://openalex.org/W2167224731","https://openalex.org/W2201912979","https://openalex.org/W2290354866","https://openalex.org/W2296673577","https://openalex.org/W2421020186","https://openalex.org/W2604726708","https://openalex.org/W2607198029","https://openalex.org/W2610395436","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2883112541","https://openalex.org/W2889347284","https://openalex.org/W2905364877","https://openalex.org/W2908470496","https://openalex.org/W2938421504","https://openalex.org/W2962902376","https://openalex.org/W2963099939","https://openalex.org/W2963165111","https://openalex.org/W2963411833","https://openalex.org/W2963484919","https://openalex.org/W2963590100","https://openalex.org/W2963864421","https://openalex.org/W2963923407","https://openalex.org/W2963940579","https://openalex.org/W2964001908","https://openalex.org/W2964021598","https://openalex.org/W2964036701","https://openalex.org/W2964161785","https://openalex.org/W2964291307","https://openalex.org/W2964333597","https://openalex.org/W2964342357","https://openalex.org/W2966564143","https://openalex.org/W2967727187","https://openalex.org/W2968268581","https://openalex.org/W2968340082","https://openalex.org/W3021593779","https://openalex.org/W6629881138","https://openalex.org/W6637967152","https://openalex.org/W6638088447","https://openalex.org/W6653435097","https://openalex.org/W6674884181","https://openalex.org/W6680657880","https://openalex.org/W6682849425","https://openalex.org/W6684338915","https://openalex.org/W6684921986","https://openalex.org/W6696324988","https://openalex.org/W6696380822","https://openalex.org/W6697540296","https://openalex.org/W6736609842","https://openalex.org/W6736742618","https://openalex.org/W6737327832","https://openalex.org/W6740801417","https://openalex.org/W6747473740","https://openalex.org/W6748012927","https://openalex.org/W6748839928","https://openalex.org/W6753060773","https://openalex.org/W6753243525","https://openalex.org/W6754162236","https://openalex.org/W6755230031","https://openalex.org/W6756848961"],"related_works":["https://openalex.org/W3109409708","https://openalex.org/W3138650132","https://openalex.org/W2951961145","https://openalex.org/W2952672470","https://openalex.org/W3035756007","https://openalex.org/W3024554557","https://openalex.org/W2950268955","https://openalex.org/W2985871261","https://openalex.org/W2980897231","https://openalex.org/W2626804490","https://openalex.org/W3093541907","https://openalex.org/W3203056473","https://openalex.org/W2963199420","https://openalex.org/W3149922422","https://openalex.org/W2996006200","https://openalex.org/W2100370041","https://openalex.org/W3046387304","https://openalex.org/W2785712252","https://openalex.org/W2963293747","https://openalex.org/W1863534978"],"abstract_inverted_index":{"Connector":[0],"insertion":[1,109],"and":[2,16,37,79,114,122],"many":[3],"other":[4],"tasks":[5,110,144],"commonly":[6],"found":[7],"in":[8,35,59,72,83],"modern":[9],"manufacturing":[10],"settings":[11],"involve":[12],"complex":[13],"contact":[14],"dynamics":[15],"friction.":[17],"Since":[18],"it":[19],"is":[20],"difficult":[21,107],"to":[22,42,53,91],"capture":[23],"related":[24],"physical":[25],"effects":[26],"with":[27,65,111,132],"first-order":[28],"modeling,":[29],"traditional":[30],"control":[31],"methods":[32,49,128],"often":[33],"result":[34],"brittle":[36],"inaccurate":[38],"controllers,":[39],"which":[40],"have":[41,50],"be":[43,54],"manually":[44],"tuned.":[45],"Reinforcement":[46],"learning":[47,57],"(RL)":[48],"been":[51],"demonstrated":[52],"capable":[55],"of":[56,106,149],"controllers":[58,138],"such":[60,135],"environments":[61],"from":[62,145],"autonomous":[63],"interaction":[64],"the":[66,73],"environment,":[67],"but":[68],"running":[69],"RL":[70,131],"algorithms":[71],"real":[74],"world":[75],"poses":[76],"sample":[77],"efficiency":[78],"safety":[80],"challenges.":[81],"Moreover,":[82],"practical":[84],"real-world":[85,150],"settings,":[86],"we":[87,102],"cannot":[88],"assume":[89],"access":[90],"perfect":[92],"state":[93],"information":[94],"or":[95,139],"dense":[96],"reward":[97,117],"signals.":[98],"In":[99],"this":[100],"paper,":[101],"consider":[103],"a":[104,146],"variety":[105],"industrial":[108],"visual":[112],"inputs":[113],"different":[115],"natural":[116],"specifications,":[118],"namely":[119],"sparse":[120],"rewards":[121],"goal":[123],"images.":[124],"We":[125],"show":[126],"that":[127,129],"combine":[130],"prior":[133],"information,":[134],"as":[136],"classical":[137],"demonstrations,":[140],"can":[141],"solve":[142],"these":[143],"reasonable":[147],"amount":[148],"interaction.":[151]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}