{"id":"https://openalex.org/W2529658650","doi":"https://doi.org/10.1109/iros.2017.8202141","title":"Collective robot reinforcement learning with distributed asynchronous guided policy search","display_name":"Collective robot reinforcement learning with distributed asynchronous guided policy search","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2529658650","doi":"https://doi.org/10.1109/iros.2017.8202141","mag":"2529658650"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2017.8202141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8202141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1610.00673","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069879254","display_name":"Ali Abdullah Yahya","orcid":"https://orcid.org/0000-0002-7805-1225"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ali Yahya","raw_affiliation_strings":["X, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"X, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025313946","display_name":"Adrian Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adrian Li","raw_affiliation_strings":["X, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"X, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080415080","display_name":"Mrinal Kalakrishnan","orcid":"https://orcid.org/0000-0003-4292-9857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mrinal Kalakrishnan","raw_affiliation_strings":["X, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"X, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001178359","display_name":"Yevgen Chebotar","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yevgen Chebotar","raw_affiliation_strings":["Department of Computer Science, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["Google Brain, Mountain View, CA, USA"],"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069879254"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.7851,"has_fulltext":false,"cited_by_count":138,"citation_normalized_percentile":{"value":0.99194092,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"79","last_page":"86"},"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":0.9987000226974487,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.8570694923400879},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.8244638442993164},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7490459680557251},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7387583255767822},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7132972478866577},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6020645499229431},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5654182434082031},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4641401171684265},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.42890626192092896},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.41024166345596313},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3746841251850128},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.36589735746383667},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32951921224594116},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.22102591395378113},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09935116767883301},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06638601422309875}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8570694923400879},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8244638442993164},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7490459680557251},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7387583255767822},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7132972478866577},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6020645499229431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5654182434082031},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4641401171684265},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.42890626192092896},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.41024166345596313},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3746841251850128},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36589735746383667},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32951921224594116},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.22102591395378113},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09935116767883301},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06638601422309875},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2017.8202141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8202141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1610.00673","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1610.00673","pdf_url":"https://arxiv.org/pdf/1610.00673","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1610.00673","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1610.00673","pdf_url":"https://arxiv.org/pdf/1610.00673","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":[{"id":"https://metadata.un.org/sdg/16","score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W195033972","https://openalex.org/W1499669280","https://openalex.org/W1771410628","https://openalex.org/W1925816294","https://openalex.org/W1986533639","https://openalex.org/W2006273250","https://openalex.org/W2011685039","https://openalex.org/W2012587148","https://openalex.org/W2085302753","https://openalex.org/W2109008048","https://openalex.org/W2110304639","https://openalex.org/W2111967991","https://openalex.org/W2121103318","https://openalex.org/W2150695437","https://openalex.org/W2155007355","https://openalex.org/W2166706236","https://openalex.org/W2168231600","https://openalex.org/W2186601217","https://openalex.org/W2293467699","https://openalex.org/W2336650964","https://openalex.org/W2510228645","https://openalex.org/W2520352517","https://openalex.org/W2529601334","https://openalex.org/W2575705757","https://openalex.org/W2919115771","https://openalex.org/W2949608212","https://openalex.org/W2952422028","https://openalex.org/W2953057288","https://openalex.org/W2953326790","https://openalex.org/W2962736495","https://openalex.org/W2963630259","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W3005581722","https://openalex.org/W3101102451","https://openalex.org/W4205513846","https://openalex.org/W4297802064","https://openalex.org/W6607786297","https://openalex.org/W6638018090","https://openalex.org/W6640290305","https://openalex.org/W6676560026","https://openalex.org/W6678367057","https://openalex.org/W6682270173","https://openalex.org/W6682849425","https://openalex.org/W6684249991","https://openalex.org/W6684859321","https://openalex.org/W6684921986","https://openalex.org/W6686786811","https://openalex.org/W6692846177","https://openalex.org/W6703420464","https://openalex.org/W6725508859","https://openalex.org/W6732386917"],"related_works":["https://openalex.org/W2930863966","https://openalex.org/W3134526803","https://openalex.org/W2126211886","https://openalex.org/W3153786280","https://openalex.org/W3127551068","https://openalex.org/W2165180011","https://openalex.org/W3165944253","https://openalex.org/W4220829754","https://openalex.org/W2351343564","https://openalex.org/W2170052867"],"abstract_inverted_index":{"Policy":[0],"search":[1,119],"methods":[2],"and,":[3],"more":[4],"broadly,":[5],"reinforcement":[6],"learning":[7,93,127,142,168,177],"can":[8,146,189],"enable":[9],"robots":[10,70],"to":[11,22,58,71,97,123],"learn":[12,80],"highly":[13],"complex":[14],"and":[15,27,51,78,90,100,113,120,143,154,173,178],"general":[16],"skills":[17],"that":[18,37,166,174,187],"may":[19],"allow":[20],"them":[21],"function":[23],"amid":[24],"the":[25,30],"complexity":[26],"diversity":[28,52],"of":[29,44,53,116,160],"real":[31],"world.":[32],"However,":[33],"training":[34,102,171],"a":[35,41,61,81,95,111,129,156,194],"policy":[36,82,92,118,126,141,176],"generalizes":[38],"well":[39],"across":[40,151],"wide":[42],"range":[43],"real-world":[45,106,196],"conditions":[46],"requires":[47],"far":[48],"greater":[49],"quantity":[50],"experience":[54,74],"than":[55],"is":[56,66],"practical":[57],"collect":[59],"with":[60,75],"single":[62],"robot.":[63],"Fortunately,":[64],"it":[65,122],"possible":[67],"for":[68],"multiple":[69,152],"share":[72],"their":[73],"one":[76],"another,":[77],"thereby,":[79],"collectively.":[83],"In":[84],"this":[85],"work,":[86],"we":[87,188],"explore":[88],"distributed":[89,112,167],"asynchronous":[91,114],"as":[94],"means":[96],"achieve":[98,190],"generalization":[99,192],"improved":[101],"times":[103],"on":[104,128,193],"challenging,":[105],"manipulation":[107],"tasks.":[108],"We":[109,137,184],"propose":[110],"version":[115],"guided":[117],"use":[121],"demonstrate":[124,186],"collective":[125],"vision-based":[130],"door":[131,197],"opening":[132,198],"task":[133],"using":[134],"four":[135],"robots.":[136],"describe":[138],"how":[139],"both":[140],"data":[144,179],"collection":[145,180],"be":[147],"conducted":[148],"in":[149],"parallel":[150],"robots,":[153],"present":[155],"detailed":[157],"empirical":[158],"evaluation":[159],"our":[161],"system.":[162],"Our":[163],"results":[164],"indicate":[165],"significantly":[169],"improves":[170,182],"time,":[172],"parallelizing":[175],"substantially":[181],"utilization.":[183],"also":[185],"substantial":[191],"challenging":[195],"task.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":9}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
