{"id":"https://openalex.org/W4407637826","doi":"https://doi.org/10.1109/tac.2025.3543128","title":"Asynchronous Parallel Policy Gradient Methods for the Linear Quadratic Regulator","display_name":"Asynchronous Parallel Policy Gradient Methods for the Linear Quadratic Regulator","publication_year":2025,"publication_date":"2025-02-17","ids":{"openalex":"https://openalex.org/W4407637826","doi":"https://doi.org/10.1109/tac.2025.3543128"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2025.3543128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3543128","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-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/A5026081309","display_name":"Feiran Zhao","orcid":"https://orcid.org/0000-0003-3142-2903"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Feiran Zhao","raw_affiliation_strings":["Department of Automation and BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064528716","display_name":"Xingyu Sha","orcid":"https://orcid.org/0000-0001-9673-302X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyu Sha","raw_affiliation_strings":["Department of Automation and BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088962631","display_name":"Keyou You","orcid":"https://orcid.org/0000-0003-4355-5340"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keyou You","raw_affiliation_strings":["Department of Automation and BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation and BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5026081309"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02885772,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"70","issue":"7","first_page":"4920","last_page":"4927"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9957000017166138,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9957000017166138,"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/T12288","display_name":"Optimization and Search Problems","score":0.979200005531311,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.978600025177002,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/regulator","display_name":"Regulator","score":0.6551617383956909},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6421653628349304},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.5836946964263916},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.5575740337371826},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4739373028278351},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4627276659011841},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4025932550430298},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3586331605911255},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3323000371456146},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.2925271987915039},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.14709049463272095},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.13542255759239197},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12250441312789917},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09015876054763794}],"concepts":[{"id":"https://openalex.org/C6929976","wikidata":"https://www.wikidata.org/wiki/Q3771881","display_name":"Regulator","level":3,"score":0.6551617383956909},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6421653628349304},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.5836946964263916},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.5575740337371826},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4739373028278351},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4627276659011841},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4025932550430298},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3586331605911255},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3323000371456146},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2925271987915039},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.14709049463272095},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.13542255759239197},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12250441312789917},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09015876054763794},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2025.3543128","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3543128","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1850434087","display_name":null,"funder_award_id":"62033006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3518171487","display_name":null,"funder_award_id":"62325305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W177930832","https://openalex.org/W2066686615","https://openalex.org/W2885464805","https://openalex.org/W2904304778","https://openalex.org/W2930863966","https://openalex.org/W2994779380","https://openalex.org/W3099880469","https://openalex.org/W3127561923","https://openalex.org/W3166923021","https://openalex.org/W3185181536","https://openalex.org/W3206480318","https://openalex.org/W3213818741","https://openalex.org/W4250954493","https://openalex.org/W4313591116","https://openalex.org/W4367841446","https://openalex.org/W4376478835","https://openalex.org/W4386147959","https://openalex.org/W4402300769","https://openalex.org/W4410342707","https://openalex.org/W6622473587","https://openalex.org/W6662929504","https://openalex.org/W6683204974","https://openalex.org/W6692846177","https://openalex.org/W6714879114","https://openalex.org/W6748638692","https://openalex.org/W6754297394","https://openalex.org/W6756870468","https://openalex.org/W6762982123","https://openalex.org/W6769580333","https://openalex.org/W6838579793","https://openalex.org/W6838828081","https://openalex.org/W6856078685"],"related_works":["https://openalex.org/W2354064740","https://openalex.org/W2731754693","https://openalex.org/W267916353","https://openalex.org/W2326995340","https://openalex.org/W1985169903","https://openalex.org/W2152693275","https://openalex.org/W311622956","https://openalex.org/W1592622096","https://openalex.org/W2122083069","https://openalex.org/W2050309662"],"abstract_inverted_index":{"Learning":[0],"policies":[1],"in":[2,67,107,120],"an":[3],"asynchronous":[4,35,117],"parallel":[5,36,118],"way":[6],"is":[7,77],"essential":[8],"to":[9,42,57,79,89],"numerous":[10],"successes":[11],"of":[12,98,115],"reinforcement":[13],"learning":[14,121],"for":[15,71],"solving":[16],"complex":[17],"problems.":[18],"However,":[19],"their":[20],"convergence":[21,96],"has":[22],"not":[23],"been":[24],"rigorously":[25],"evaluated.":[26],"To":[27],"improve":[28],"the":[29,34,44,82,95,113],"theoretical":[30],"understanding,":[31],"we":[32,100],"adopt":[33],"zero-order":[37,59],"policy":[38,60,72],"gradient":[39],"(AZOPG)":[40],"method":[41],"solve":[43],"continuous-time":[45],"linear":[46,103],"quadratic":[47],"regulation":[48],"problem.":[49],"Specifically,":[50],"multiple":[51],"workers":[52,119],"independently":[53],"perform":[54],"system":[55],"rollouts":[56],"estimate":[58],"gradients":[61],"(PGs),":[62],"which":[63,111],"are":[64],"then":[65],"aggregated":[66],"a":[68,102],"central":[69,83],"node":[70,84],"updates.":[73],"Moreover,":[74],"each":[75],"worker":[76],"allowed":[78],"interact":[80],"with":[81],"<italic":[85],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[86],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">asynchronously</i>,":[87],"leading":[88],"delayed":[90],"PG":[91],"estimates.":[92],"By":[93],"quantifying":[94],"rate":[97],"AZOPG,":[99],"show":[101],"speedup":[104],"property":[105],"both":[106],"theory":[108],"and":[109],"simulation,":[110],"reveals":[112],"advantages":[114],"using":[116],"policies.":[122]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}