{"id":"https://openalex.org/W2575705757","doi":"https://doi.org/10.1109/icra.2017.7989385","title":"Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates","display_name":"Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2575705757","doi":"https://doi.org/10.1109/icra.2017.7989385","mag":"2575705757"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2017.7989385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5061613634","display_name":"Shixiang Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Shixiang Gu","raw_affiliation_strings":["MPI T\u00fcbingen","University of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MPI T\u00fcbingen","institution_ids":[]},{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005863569","display_name":"Ethan Holly","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":"Ethan Holly","raw_affiliation_strings":["Google Brain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066294254","display_name":"Timothy Lillicrap","orcid":"https://orcid.org/0000-0001-8918-486X"},"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/I4210090411","display_name":"DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Timothy Lillicrap","raw_affiliation_strings":["Google DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google DeepMind","institution_ids":["https://openalex.org/I1291425158","https://openalex.org/I4210090411"]}]},{"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/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"]},{"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":"Sergey Levine","raw_affiliation_strings":["Google Brain","UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061613634"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":120.5936,"has_fulltext":false,"cited_by_count":1452,"citation_normalized_percentile":{"value":0.9996299,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3389","last_page":"3396"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9987999796867371,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.9360231161117554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7730343341827393},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.667828381061554},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6477953791618347},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5727950930595398},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5457841157913208},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48617619276046753},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4354930818080902},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33534514904022217}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9360231161117554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7730343341827393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.667828381061554},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6477953791618347},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5727950930595398},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5457841157913208},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48617619276046753},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4354930818080902},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33534514904022217},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra.2017.7989385","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989385","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.mpg.de:item_2564870","is_oa":false,"landing_page_url":"http://hdl.handle.net/21.11116/0000-0000-F9E4-6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400654","display_name":"MPG.PuRe (Max Planck Society)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149899117","host_organization_name":"Max Planck Society","host_organization_lineage":["https://openalex.org/I149899117"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA 2017)","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1482341360","https://openalex.org/W1499669280","https://openalex.org/W1522301498","https://openalex.org/W1771410628","https://openalex.org/W1825869920","https://openalex.org/W1836465849","https://openalex.org/W1968962398","https://openalex.org/W1969705022","https://openalex.org/W1977655452","https://openalex.org/W1986533639","https://openalex.org/W2001095967","https://openalex.org/W2011685039","https://openalex.org/W2012587148","https://openalex.org/W2038794597","https://openalex.org/W2051620263","https://openalex.org/W2085302753","https://openalex.org/W2100235553","https://openalex.org/W2119717200","https://openalex.org/W2125612430","https://openalex.org/W2139053308","https://openalex.org/W2140135625","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2161395589","https://openalex.org/W2161872510","https://openalex.org/W2162426968","https://openalex.org/W2168945912","https://openalex.org/W2169209873","https://openalex.org/W2290354866","https://openalex.org/W2529658650","https://openalex.org/W2584377191","https://openalex.org/W2950471160","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964121744","https://openalex.org/W2964161785","https://openalex.org/W4205513846","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6638667902","https://openalex.org/W6680657880","https://openalex.org/W6682849425","https://openalex.org/W6683204974","https://openalex.org/W6684786618","https://openalex.org/W6684921986","https://openalex.org/W6685331716","https://openalex.org/W6692846177","https://openalex.org/W6696324988","https://openalex.org/W6727962482","https://openalex.org/W6732837357","https://openalex.org/W7073827480"],"related_works":["https://openalex.org/W2116677773","https://openalex.org/W2155261584","https://openalex.org/W2584231425","https://openalex.org/W2042919702","https://openalex.org/W2150611273","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4207086172","https://openalex.org/W4380318855","https://openalex.org/W4225981436"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,25,32,59,75,106],"holds":[2],"the":[3,28,31,140,149],"promise":[4],"of":[5,13,23,30,36,71,112,171],"enabling":[6],"autonomous":[7],"robots":[8,153,185],"to":[9,82,90,117,131],"learn":[10,124,168],"large":[11],"repertoires":[12],"behavioral":[14],"skills":[15,174],"with":[16],"minimal":[17],"human":[18],"intervention.":[19],"However,":[20],"robotic":[21],"applications":[22,70],"reinforcement":[24,58,74,105],"often":[26],"compromise":[27],"autonomy":[29],"process":[33],"in":[34,175],"favor":[35],"achieving":[37],"training":[38,64,111,141],"times":[39,142],"that":[40,101,139,164],"are":[41],"practical":[42],"for":[43],"real":[44,134,184],"physical":[45,135],"systems.":[46],"This":[47],"typically":[48],"involves":[49],"introducing":[50],"hand-engineered":[51],"policy":[52,157],"representations":[53],"and":[54,85,122,177],"human-supplied":[55],"demonstrations.":[56],"Deep":[57],"alleviates":[60],"this":[61,97],"limitation":[62],"by":[63,147],"general-purpose":[65],"neural":[66,126],"network":[67,127],"policies,":[68],"but":[69],"direct":[72],"deep":[73,104,113,125],"algorithms":[76],"have":[77],"so":[78],"far":[79],"been":[80],"restricted":[81],"simulated":[83],"settings":[84],"relatively":[86],"simple":[87],"tasks,":[88],"due":[89],"their":[91,156],"apparent":[92],"high":[93],"sample":[94],"complexity.":[95],"In":[96],"paper,":[98],"we":[99],"demonstrate":[100,138],"a":[102,169,178],"recent":[103],"algorithm":[107,150],"based":[108],"on":[109,133,183],"off-policy":[110],"Q-functions":[114],"can":[115,123,143,167],"scale":[116],"complex":[118,179],"3D":[119,172],"manipulation":[120,173],"tasks":[121],"policies":[128],"efficiently":[129],"enough":[130],"train":[132],"robots.":[136],"We":[137],"be":[144],"further":[145],"reduced":[146],"parallelizing":[148],"across":[151],"multiple":[152],"which":[154],"pool":[155],"updates":[158],"asynchronously.":[159],"Our":[160],"experimental":[161],"evaluation":[162],"shows":[163],"our":[165],"method":[166],"variety":[170],"simulation":[176],"door":[180],"opening":[181],"skill":[182],"without":[186],"any":[187],"prior":[188],"demonstrations":[189],"or":[190],"manually":[191],"designed":[192],"representations.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":23},{"year":2025,"cited_by_count":97},{"year":2024,"cited_by_count":111},{"year":2023,"cited_by_count":186},{"year":2022,"cited_by_count":176},{"year":2021,"cited_by_count":274},{"year":2020,"cited_by_count":260},{"year":2019,"cited_by_count":184},{"year":2018,"cited_by_count":109},{"year":2017,"cited_by_count":31},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-06T09:05:17.133730","created_date":"2025-10-10T00:00:00"}