{"id":"https://openalex.org/W4221141531","doi":"https://doi.org/10.1109/icra46639.2022.9811771","title":"Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots","display_name":"Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots","publication_year":2022,"publication_date":"2022-05-23","ids":{"openalex":"https://openalex.org/W4221141531","doi":"https://doi.org/10.1109/icra46639.2022.9811771"},"language":"en","primary_location":{"id":"doi:10.1109/icra46639.2022.9811771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811771","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5014384556","display_name":"Yufeng Yuan","orcid":"https://orcid.org/0000-0003-3924-3803"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yufeng Yuan","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton,Canada,T6G 2E8"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton,Canada,T6G 2E8","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102815213","display_name":"A. Rupam Mahmood","orcid":"https://orcid.org/0000-0002-2640-1844"},"institutions":[{"id":"https://openalex.org/I125680101","display_name":"Turing Institute","ror":"https://ror.org/02x2mw849","country_code":"GB","type":"facility","lineage":["https://openalex.org/I125680101"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA","GB","US"],"is_corresponding":false,"raw_author_name":"A. Rupam Mahmood","raw_affiliation_strings":["University of Alberta,Department of Computing Science,Edmonton,Canada,T6G 2E8","CIFAR AI Chair, Alberta Machine Intelligence Institute (Amii)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alberta,Department of Computing Science,Edmonton,Canada,T6G 2E8","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"CIFAR AI Chair, Alberta Machine Intelligence Institute (Amii)","institution_ids":["https://openalex.org/I125680101","https://openalex.org/I1343180700"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2458,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.80948847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5546","last_page":"5552"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8511637449264526},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8397136926651001},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.8085935115814209},{"id":"https://openalex.org/keywords/asynchronous-learning","display_name":"Asynchronous learning","score":0.5517324805259705},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5091931223869324},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4869993329048157},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.46073031425476074},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4508979320526123},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4441084563732147},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.43727970123291016},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4189738631248474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39649778604507446},{"id":"https://openalex.org/keywords/synchronous-learning","display_name":"Synchronous learning","score":0.27564185857772827},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.19947153329849243},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1340532898902893},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.12562787532806396},{"id":"https://openalex.org/keywords/cooperative-learning","display_name":"Cooperative learning","score":0.11747843027114868},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09990209341049194}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8511637449264526},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8397136926651001},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.8085935115814209},{"id":"https://openalex.org/C2777072894","wikidata":"https://www.wikidata.org/wiki/Q4812204","display_name":"Asynchronous learning","level":5,"score":0.5517324805259705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5091931223869324},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4869993329048157},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.46073031425476074},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4508979320526123},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4441084563732147},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.43727970123291016},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4189738631248474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39649778604507446},{"id":"https://openalex.org/C19122763","wikidata":"https://www.wikidata.org/wiki/Q7662215","display_name":"Synchronous learning","level":4,"score":0.27564185857772827},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.19947153329849243},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1340532898902893},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.12562787532806396},{"id":"https://openalex.org/C51672120","wikidata":"https://www.wikidata.org/wiki/Q303446","display_name":"Cooperative learning","level":3,"score":0.11747843027114868},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09990209341049194},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C88610354","wikidata":"https://www.wikidata.org/wiki/Q1813494","display_name":"Teaching method","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra46639.2022.9811771","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra46639.2022.9811771","pdf_url":null,"source":{"id":"https://openalex.org/S4363607759","display_name":"2022 International Conference on Robotics and Automation (ICRA)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320314212","display_name":"Alberta Machine Intelligence Institute","ror":null},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1658008008","https://openalex.org/W1771410628","https://openalex.org/W1968962398","https://openalex.org/W2142441581","https://openalex.org/W2342662072","https://openalex.org/W2575705757","https://openalex.org/W2736601468","https://openalex.org/W2767050701","https://openalex.org/W2784465508","https://openalex.org/W2798705390","https://openalex.org/W2810785043","https://openalex.org/W2904246096","https://openalex.org/W2907537824","https://openalex.org/W2914688076","https://openalex.org/W2950268955","https://openalex.org/W2950872548","https://openalex.org/W2963634205","https://openalex.org/W2963780574","https://openalex.org/W2963864421","https://openalex.org/W2964227158","https://openalex.org/W2977481643","https://openalex.org/W2990747716","https://openalex.org/W3013146177","https://openalex.org/W3020712699","https://openalex.org/W3021708257","https://openalex.org/W3101442004","https://openalex.org/W4287667696","https://openalex.org/W4287811291","https://openalex.org/W4287824211","https://openalex.org/W4297797010","https://openalex.org/W4298857966","https://openalex.org/W6636881020","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6684921986","https://openalex.org/W6688347243","https://openalex.org/W6704571135","https://openalex.org/W6729556111","https://openalex.org/W6732386917","https://openalex.org/W6741002519","https://openalex.org/W6746595151","https://openalex.org/W6747790125","https://openalex.org/W6748638692","https://openalex.org/W6749115525","https://openalex.org/W6753243525","https://openalex.org/W6754615820","https://openalex.org/W6757592117","https://openalex.org/W6768511085","https://openalex.org/W6771179988","https://openalex.org/W6776867236","https://openalex.org/W6776901495","https://openalex.org/W6782858274"],"related_works":["https://openalex.org/W4294338060","https://openalex.org/W1491017262","https://openalex.org/W1494824878","https://openalex.org/W4297819361","https://openalex.org/W4226047841","https://openalex.org/W2156559761","https://openalex.org/W3020208395","https://openalex.org/W2496167052","https://openalex.org/W1956936791","https://openalex.org/W2041343407"],"abstract_inverted_index":{"An":[0],"oft-ignored":[1],"challenge":[2],"of":[3,30,35,143,178,208],"real-world":[4,92],"reinforcement":[5,87,122],"learning":[6,18,42,71,88,110,123,144,172,180,187,217],"is":[7,183,223],"that":[8,112,138],"the":[9,54,140,147,159,176],"real":[10,55,215],"world":[11],"does":[12,211],"not":[13,25,67],"pause":[14],"when":[15,48,139,171],"agents":[16],"make":[17,59],"updates.":[19],"As":[20,45],"standard":[21],"simulated":[22],"environments":[23],"do":[24],"address":[26],"this":[27,77,95],"real-time":[28,196],"aspect":[29],"learning,":[31],"most":[32],"available":[33,224],"implementations":[34,50],"RL":[36],"algorithms":[37],"process":[38],"environment":[39],"interactions":[40],"and":[41,66,85,117,120,132,182,199,210],"updates":[43,145,173],"sequentially.":[44],"a":[46,104,114,189],"consequence,":[47],"such":[49],"are":[51,174],"deployed":[52],"in":[53,151,195],"world,":[56],"they":[57],"may":[58],"decisions":[60],"based":[61],"on":[62],"significantly":[63],"delayed":[64],"observations":[65],"act":[68],"responsively.":[69],"Asynchronous":[70],"has":[72],"been":[73],"proposed":[74],"to":[75,197],"solve":[76],"issue,":[78],"but":[79],"no":[80],"systematic":[81],"comparison":[82],"between":[83],"sequential":[84,119,152,179],"asynchronous":[86,109,121,160,186],"was":[89],"conducted":[90],"using":[91,214],"environments.":[93],"In":[94],"work,":[96],"we":[97],"set":[98],"up":[99],"two":[100,206],"vision-based":[101],"tasks":[102],"with":[103],"robotic":[105],"arm,":[106],"implement":[107],"an":[108,165],"system":[111,193],"extends":[113],"previous":[115],"architecture,":[116],"compare":[118],"across":[124],"different":[125],"action":[126,148,167],"cycle":[127,149,168],"times,":[128],"sensory":[129],"data":[130],"dimensions,":[131],"mini-batch":[133],"sizes.":[134],"Our":[135,192,221],"experiments":[136],"show":[137],"time":[141,150],"cost":[142],"increases,":[146],"implementation":[153,161],"could":[154],"grow":[155],"excessively":[156],"long,":[157],"while":[158],"can":[162],"always":[163],"maintain":[164],"appropriate":[166],"time.":[169],"Consequently,":[170],"expensive,":[175],"performance":[177],"diminishes":[181],"outperformed":[184],"by":[185,188],"substantial":[190],"margin.":[191],"learns":[194],"reach":[198],"track":[200],"visual":[201],"targets":[202],"from":[203,219],"pixels":[204],"within":[205],"hours":[207],"experience":[209],"so":[212],"directly":[213],"robots,":[216],"completely":[218],"scratch.":[220],"code":[222],"at:":[225],"https://github.com/YufengYuan/ur5_async_r1.":[226]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}