{"id":"https://openalex.org/W4394586218","doi":"https://doi.org/10.1109/tac.2024.3386061","title":"Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent","display_name":"Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent","publication_year":2024,"publication_date":"2024-04-08","ids":{"openalex":"https://openalex.org/W4394586218","doi":"https://doi.org/10.1109/tac.2024.3386061"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2024.3386061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3386061","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/A5073846906","display_name":"Gangshan Jing","orcid":"https://orcid.org/0000-0003-0066-204X"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gangshan Jing","raw_affiliation_strings":["Chongqing University, Chongqing, China","Chongqing University, Chongqing, P.R. China"],"affiliations":[{"raw_affiliation_string":"Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]},{"raw_affiliation_string":"Chongqing University, Chongqing, P.R. China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040513070","display_name":"He Bai","orcid":"https://orcid.org/0000-0002-4247-0698"},"institutions":[{"id":"https://openalex.org/I115475287","display_name":"Oklahoma State University","ror":"https://ror.org/01g9vbr38","country_code":"US","type":"education","lineage":["https://openalex.org/I115475287"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He Bai","raw_affiliation_strings":["Oklahoma State University, Stillwater, OK, USA"],"affiliations":[{"raw_affiliation_string":"Oklahoma State University, Stillwater, OK, USA","institution_ids":["https://openalex.org/I115475287"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054187846","display_name":"Jemin George","orcid":"https://orcid.org/0000-0001-8417-5411"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jemin George","raw_affiliation_strings":["DEVCOM Army Research Laboratory, Adelphi, MD, USA"],"affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055360778","display_name":"Aranya Chakrabortty","orcid":"https://orcid.org/0000-0002-3474-8215"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aranya Chakrabortty","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078394771","display_name":"P. Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]},{"id":"https://openalex.org/I2802705668","display_name":"United States Army Combat Capabilities Development Command","ror":"https://ror.org/02rdkx920","country_code":"US","type":"other","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piyush K. Sharma","raw_affiliation_strings":["DEVCOM Army Research Laboratory, Adelphi, MD, USA"],"affiliations":[{"raw_affiliation_string":"DEVCOM Army Research Laboratory, Adelphi, MD, USA","institution_ids":["https://openalex.org/I166416128","https://openalex.org/I2802705668"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073846906"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":1.7169,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8442922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"69","issue":"11","first_page":"7524","last_page":"7539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9994000196456909,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12676","display_name":"Machine Learning and ELM","score":0.9941999912261963,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7204815745353699},{"id":"https://openalex.org/keywords/coordinate-descent","display_name":"Coordinate descent","score":0.7013556361198425},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.6744011044502258},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6401535272598267},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.6277511119842529},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5713955163955688},{"id":"https://openalex.org/keywords/zeroth-law-of-thermodynamics","display_name":"Zeroth law of thermodynamics","score":0.5624353885650635},{"id":"https://openalex.org/keywords/coordinate-system","display_name":"Coordinate system","score":0.4570498764514923},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.35631102323532104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23384112119674683},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21948418021202087},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18361881375312805},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09024757146835327},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07006415724754333}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7204815745353699},{"id":"https://openalex.org/C157553263","wikidata":"https://www.wikidata.org/wiki/Q5168004","display_name":"Coordinate descent","level":2,"score":0.7013556361198425},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.6744011044502258},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6401535272598267},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.6277511119842529},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5713955163955688},{"id":"https://openalex.org/C68755742","wikidata":"https://www.wikidata.org/wiki/Q190983","display_name":"Zeroth law of thermodynamics","level":2,"score":0.5624353885650635},{"id":"https://openalex.org/C80551277","wikidata":"https://www.wikidata.org/wiki/Q11210","display_name":"Coordinate system","level":2,"score":0.4570498764514923},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.35631102323532104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23384112119674683},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21948418021202087},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18361881375312805},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09024757146835327},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07006415724754333},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2024.3386061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3386061","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/G5361399887","display_name":null,"funder_award_id":"2212582","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921719111","display_name":null,"funder_award_id":"62203073","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6266620356","display_name":null,"funder_award_id":"2241585","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7416579264","display_name":null,"funder_award_id":"ECCS 1931932","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W153281708","https://openalex.org/W203276351","https://openalex.org/W1833417691","https://openalex.org/W1918371733","https://openalex.org/W1981826826","https://openalex.org/W2000769684","https://openalex.org/W2004001705","https://openalex.org/W2032291279","https://openalex.org/W2067484689","https://openalex.org/W2091638851","https://openalex.org/W2095984592","https://openalex.org/W2117686388","https://openalex.org/W2135519533","https://openalex.org/W2149479912","https://openalex.org/W2226862355","https://openalex.org/W2560814118","https://openalex.org/W2746600820","https://openalex.org/W2788115019","https://openalex.org/W2795577721","https://openalex.org/W2808494755","https://openalex.org/W2886474253","https://openalex.org/W2904304778","https://openalex.org/W2908153988","https://openalex.org/W2938668169","https://openalex.org/W2951896791","https://openalex.org/W2953043436","https://openalex.org/W2963308146","https://openalex.org/W2963648037","https://openalex.org/W2963774238","https://openalex.org/W2964305565","https://openalex.org/W2972523776","https://openalex.org/W2993990522","https://openalex.org/W2995134936","https://openalex.org/W3045976685","https://openalex.org/W3046992251","https://openalex.org/W3082658705","https://openalex.org/W3106412272","https://openalex.org/W3107686539","https://openalex.org/W3119327948","https://openalex.org/W3126784434","https://openalex.org/W3131256831","https://openalex.org/W3134022240","https://openalex.org/W3155542523","https://openalex.org/W3155557419","https://openalex.org/W3157457774","https://openalex.org/W3163894240","https://openalex.org/W3187695488","https://openalex.org/W3200431459","https://openalex.org/W3202062745","https://openalex.org/W3213818741","https://openalex.org/W3217389438","https://openalex.org/W4210340884","https://openalex.org/W4285819774","https://openalex.org/W4299802797","https://openalex.org/W4322764374","https://openalex.org/W6606291809","https://openalex.org/W6638772632","https://openalex.org/W6638826736","https://openalex.org/W6651597697","https://openalex.org/W6736572398","https://openalex.org/W6738796088","https://openalex.org/W6749032143","https://openalex.org/W6754297394","https://openalex.org/W6756870468","https://openalex.org/W6761170661","https://openalex.org/W6764923034","https://openalex.org/W6766686101","https://openalex.org/W6771232374","https://openalex.org/W6772183843","https://openalex.org/W6782649914","https://openalex.org/W6790723713","https://openalex.org/W6791401223","https://openalex.org/W6799694710"],"related_works":["https://openalex.org/W4376654045","https://openalex.org/W2363108177","https://openalex.org/W3031701359","https://openalex.org/W2366322774","https://openalex.org/W3213349779","https://openalex.org/W4286248447","https://openalex.org/W2605503048","https://openalex.org/W3042787614","https://openalex.org/W2350747896","https://openalex.org/W2374707933"],"abstract_inverted_index":{"Recently":[0],"introduced":[1],"distributed":[2,12,61,129,134,154],"zeroth-order":[3,62],"optimization":[4,72,108],"(ZOO)":[5],"algorithms":[6],"have":[7],"shown":[8],"their":[9],"utility":[10],"in":[11,17,70,153],"reinforcement":[13],"learning":[14,141],"(RL).":[15],"Unfortunately,":[16],"the":[18,30,34,41,66,71,117,147,162],"gradient":[19,82],"estimation":[20,49],"process,":[21],"almost":[22],"all":[23],"of":[24,40,90,161],"them":[25],"require":[26,38],"random":[27],"samples":[28],"with":[29,109],"same":[31],"dimension":[32],"as":[33,127],"global":[35,42],"variable":[36],"and/or":[37],"evaluation":[39,86],"cost":[43,85],"function,":[44],"which":[45,74],"may":[46],"induce":[47],"high":[48],"variance":[50,173],"for":[51,105,133],"large-scale":[52],"networks.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"propose":[58],"a":[59,110,128,140,175],"novel":[60],"algorithm":[63,96,123,132,164],"by":[64,83],"leveraging":[65],"network":[67],"structure":[68],"inherent":[69],"objective,":[73],"allows":[75],"each":[76],"agent":[77],"to":[78,145,165],"estimate":[79],"its":[80,167],"local":[81,84],"independently,":[87],"without":[88],"use":[89],"any":[91],"consensus":[92],"protocol.":[93],"The":[94,122],"proposed":[95,163],"exhibits":[97],"an":[98,158],"asynchronous":[99],"update":[100],"scheme,":[101],"and":[102,172],"is":[103,124,143],"designed":[104,144],"stochastic":[106],"non-convex":[107,112],"possibly":[111],"feasible":[113],"domain":[114],"based":[115],"on":[116,169],"block":[118],"coordinate":[119],"descent":[120],"method.":[121],"later":[125],"employed":[126],"model-free":[130],"RL":[131],"linear":[135],"quadratic":[136],"regulator":[137],"design,":[138],"where":[139],"graph":[142],"describe":[146],"required":[148],"interaction":[149],"relationship":[150],"among":[151],"agents":[152],"learning.":[155],"We":[156],"provide":[157],"empirical":[159],"validation":[160],"benchmark":[166],"performance":[168],"convergence":[170],"rate":[171],"against":[174],"centralized":[176],"ZOO":[177],"algorithm.":[178]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2024-04-09T00:00:00"}