{"id":"https://openalex.org/W2788575380","doi":"https://doi.org/10.1109/icra.2018.8461039","title":"Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods","display_name":"Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2788575380","doi":"https://doi.org/10.1109/icra.2018.8461039","mag":"2788575380"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2018.8461039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/1802.10264","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090940643","display_name":"Deirdre Quillen","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":true,"raw_author_name":"Deirdre Quillen","raw_affiliation_strings":["Google Brain","[Google Brain]"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"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":["Google Brain","[Google Brain]"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057773393","display_name":"Ofir Nachum","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":"Ofir Nachum","raw_affiliation_strings":["Google Brain","[Google Brain]"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874"},"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":"Chelsea Finn","raw_affiliation_strings":["University of California, Berkeley","University of California\u2013Berkeley"],"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/A5053574266","display_name":"Julian Ibarz","orcid":"https://orcid.org/0000-0002-9920-6978"},"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":"Julian Ibarz","raw_affiliation_strings":["Google Brain","[Google Brain]"],"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]},{"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/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"]},{"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","[Google Brain]"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"[Google Brain]","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5090940643"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":2.7076,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.92142373,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6284","last_page":"6291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9824000000953674,"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":0.9315999746322632,"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":0.8645267486572266},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8095322847366333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7580454349517822},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.74838787317276},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6751829981803894},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6117337942123413},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6004981398582458},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5796657800674438},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5548760890960693},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5234596133232117},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4982175827026367},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4633939862251282},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10275977849960327},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08834898471832275}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8645267486572266},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8095322847366333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7580454349517822},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.74838787317276},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6751829981803894},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6117337942123413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6004981398582458},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5796657800674438},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5548760890960693},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5234596133232117},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4982175827026367},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4633939862251282},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10275977849960327},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08834898471832275},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra.2018.8461039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461039","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1802.10264","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.10264","pdf_url":"https://arxiv.org/pdf/1802.10264","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":null,"raw_type":"text"},{"id":"mag:2788575380","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1802.10264","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.1802.10264","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.10264","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:1802.10264","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.10264","pdf_url":"https://arxiv.org/pdf/1802.10264","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2788575380.pdf","grobid_xml":"https://content.openalex.org/works/W2788575380.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1981667747","https://openalex.org/W1999156278","https://openalex.org/W2036637075","https://openalex.org/W2085949256","https://openalex.org/W2088043683","https://openalex.org/W2119717200","https://openalex.org/W2150468603","https://openalex.org/W2746553466","https://openalex.org/W6606719070","https://openalex.org/W6630226614","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6642419745","https://openalex.org/W6678317597","https://openalex.org/W6678727799","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6687808982","https://openalex.org/W6688347243","https://openalex.org/W6692846177","https://openalex.org/W6696324988","https://openalex.org/W6697071109","https://openalex.org/W6704571135","https://openalex.org/W6712884540","https://openalex.org/W6726908607","https://openalex.org/W6727690138","https://openalex.org/W6728499154","https://openalex.org/W6729507393","https://openalex.org/W6731094094","https://openalex.org/W6732386917","https://openalex.org/W6734206676","https://openalex.org/W6734230652","https://openalex.org/W6734517396","https://openalex.org/W6735571901","https://openalex.org/W6736179038","https://openalex.org/W6736742618","https://openalex.org/W6737327832","https://openalex.org/W6740471745","https://openalex.org/W6740802823","https://openalex.org/W6742945991","https://openalex.org/W6743802245","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W2603178514","https://openalex.org/W3103130321","https://openalex.org/W3100226171","https://openalex.org/W2155968351","https://openalex.org/W2962872206","https://openalex.org/W2950268955","https://openalex.org/W3196282216","https://openalex.org/W2966950754","https://openalex.org/W2896268674","https://openalex.org/W2910929128","https://openalex.org/W3213106995","https://openalex.org/W2743553019","https://openalex.org/W3204843673","https://openalex.org/W2964161785","https://openalex.org/W2973387504","https://openalex.org/W3035756007","https://openalex.org/W2610395436","https://openalex.org/W3133374884","https://openalex.org/W2554830522","https://openalex.org/W3115080916"],"abstract_inverted_index":{"In":[0],"this":[1,54],"paper,":[2],"we":[3,56],"explore":[4],"deep":[5,14,125],"reinforcement":[6,15],"learning":[7,16,67,74],"algorithms":[8,32,160,178],"for":[9,45,61,121],"vision-based":[10],"robotic":[11,62,122],"grasping.":[12,51],"Model-free":[13],"(RL)":[17],"has":[18],"been":[19],"successfully":[20],"applied":[21],"to":[22,36,70,90,94,96,158],"a":[23,46,58,81,111,117,130,135,154],"range":[24],"of":[25,31,77,84,113,137,168],"challenging":[26],"environments,":[27],"but":[28],"the":[29,92,107,173,177],"proliferation":[30],"makes":[33],"it":[34],"difficult":[35],"discern":[37],"which":[38],"particular":[39],"approach":[40,132],"would":[41],"be":[42],"best":[43],"suited":[44],"rich,":[47],"diverse":[48],"task":[49],"like":[50],"To":[52],"answer":[53],"question,":[55],"propose":[57],"simulated":[59],"benchmark":[60,108],"grasping":[63,78,123],"that":[64,99,149],"emphasizes":[65],"off-policy":[66,144],"and":[68,86,129,142,165],"generalization":[69],"unseen":[71],"objects.":[72],"Off-policy":[73],"enables":[75],"utilization":[76],"data":[79],"over":[80],"wide":[82],"variety":[83,112],"objects,":[85],"diversity":[87],"is":[88],"important":[89],"enable":[91],"method":[93,118],"generalize":[95],"new":[97],"objects":[98],"were":[100],"not":[101],"seen":[102],"during":[103],"training.":[104],"We":[105],"evaluate":[106],"tasks":[109],"against":[110],"Q-function":[114],"estimation":[115,141],"methods,":[116],"previously":[119],"proposed":[120],"with":[124],"neural":[126],"network":[127],"models,":[128],"novel":[131],"based":[133],"on":[134,172],"combination":[136],"Monte":[138],"Carlo":[139],"return":[140],"an":[143],"correction.":[145],"Our":[146],"results":[147],"indicate":[148],"several":[150],"simple":[151],"methods":[152],"provide":[153],"surprisingly":[155],"strong":[156],"competitor":[157],"popular":[159],"such":[161],"as":[162],"double":[163],"Q-learning,":[164],"our":[166],"analysis":[167],"stability":[169],"sheds":[170],"light":[171],"relative":[174],"tradeoffs":[175],"between":[176],"<sup":[179],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[180],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[181],".":[182]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}