{"id":"https://openalex.org/W2994779591","doi":"https://doi.org/10.1109/tac.2021.3128592","title":"Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach","display_name":"Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach","publication_year":2021,"publication_date":"2021-11-16","ids":{"openalex":"https://openalex.org/W2994779591","doi":"https://doi.org/10.1109/tac.2021.3128592","mag":"2994779591"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2021.3128592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3128592","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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1912.09135","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100444772","display_name":"Yingying Li","orcid":"https://orcid.org/0000-0002-1858-4257"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yingying Li","raw_affiliation_strings":["John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","Harvard University ,"],"raw_orcid":"https://orcid.org/0000-0002-1858-4257","affiliations":[{"raw_affiliation_string":"John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087492658","display_name":"Yujie Tang","orcid":"https://orcid.org/0000-0002-4921-8372"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yujie Tang","raw_affiliation_strings":["John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","Harvard University ,"],"raw_orcid":"https://orcid.org/0000-0002-4921-8372","affiliations":[{"raw_affiliation_string":"John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102025389","display_name":"Runyu Zhang","orcid":"https://orcid.org/0000-0002-9333-3554"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Runyu Zhang","raw_affiliation_strings":["John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","Harvard University ,"],"raw_orcid":"https://orcid.org/0000-0002-9333-3554","affiliations":[{"raw_affiliation_string":"John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I2801851002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100368048","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-9545-3050"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I2801851002","display_name":"Harvard University Press","ror":"https://ror.org/006v7bf86","country_code":"US","type":"other","lineage":["https://openalex.org/I136199984","https://openalex.org/I2801851002"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","Harvard University ,"],"raw_orcid":"https://orcid.org/0000-0001-9545-3050","affiliations":[{"raw_affiliation_string":"John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Harvard University ,","institution_ids":["https://openalex.org/I2801851002"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7748,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.91158446,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"67","issue":"12","first_page":"6429","last_page":"6444"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9977999925613403,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9977999925613403,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9944000244140625,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9914000034332275,"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":0.7274504899978638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6180544495582581},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5934033393859863},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5482365489006042},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.49265581369400024},{"id":"https://openalex.org/keywords/trust-region","display_name":"Trust region","score":0.45637309551239014},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.44957223534584045},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.352167010307312},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2454206347465515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24060794711112976},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12586703896522522}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7274504899978638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6180544495582581},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5934033393859863},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5482365489006042},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.49265581369400024},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.45637309551239014},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.44957223534584045},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.352167010307312},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2454206347465515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24060794711112976},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12586703896522522},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C178635117","wikidata":"https://www.wikidata.org/wiki/Q747499","display_name":"RADIUS","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tac.2021.3128592","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3128592","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"},{"id":"pmh:oai:arXiv.org:1912.09135","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.09135","pdf_url":"https://arxiv.org/pdf/1912.09135","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"doi:10.48550/arxiv.1912.09135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1912.09135","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:2994779591","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1912.09135","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1912.09135","pdf_url":"https://arxiv.org/pdf/1912.09135","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2994779591.pdf","grobid_xml":"https://content.openalex.org/works/W2994779591.grobid-xml"},"referenced_works_count":79,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W1540560684","https://openalex.org/W1542941925","https://openalex.org/W1590759229","https://openalex.org/W1970181869","https://openalex.org/W1977357978","https://openalex.org/W2004001705","https://openalex.org/W2012160694","https://openalex.org/W2023356347","https://openalex.org/W2052044664","https://openalex.org/W2054314161","https://openalex.org/W2069525910","https://openalex.org/W2074796812","https://openalex.org/W2086298643","https://openalex.org/W2086977346","https://openalex.org/W2088956500","https://openalex.org/W2102041666","https://openalex.org/W2103979068","https://openalex.org/W2104602264","https://openalex.org/W2119717200","https://openalex.org/W2124141629","https://openalex.org/W2127412976","https://openalex.org/W2128870461","https://openalex.org/W2155027007","https://openalex.org/W2165150801","https://openalex.org/W2165894964","https://openalex.org/W2171830216","https://openalex.org/W2320262435","https://openalex.org/W2484646121","https://openalex.org/W2488758846","https://openalex.org/W2580602575","https://openalex.org/W2615547864","https://openalex.org/W2617547828","https://openalex.org/W2754770961","https://openalex.org/W2763533254","https://openalex.org/W2766447205","https://openalex.org/W2783297289","https://openalex.org/W2798534591","https://openalex.org/W2886474253","https://openalex.org/W2905810301","https://openalex.org/W2914218973","https://openalex.org/W2936405433","https://openalex.org/W2951896791","https://openalex.org/W2951990408","https://openalex.org/W2962938168","https://openalex.org/W2963062786","https://openalex.org/W2963470657","https://openalex.org/W2963747324","https://openalex.org/W2963774238","https://openalex.org/W2963965485","https://openalex.org/W2966348706","https://openalex.org/W2970142535","https://openalex.org/W2970161765","https://openalex.org/W2970588229","https://openalex.org/W2972441603","https://openalex.org/W2972523776","https://openalex.org/W2972915637","https://openalex.org/W3046017196","https://openalex.org/W3046992251","https://openalex.org/W3100513551","https://openalex.org/W3166923021","https://openalex.org/W3206480318","https://openalex.org/W3209135762","https://openalex.org/W4300443332","https://openalex.org/W6635285615","https://openalex.org/W6651597697","https://openalex.org/W6674948973","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6698038680","https://openalex.org/W6736572398","https://openalex.org/W6754297394","https://openalex.org/W6756870468","https://openalex.org/W6763478762","https://openalex.org/W6766686101","https://openalex.org/W6767019922","https://openalex.org/W6779257429","https://openalex.org/W6780308666","https://openalex.org/W6780486084"],"related_works":["https://openalex.org/W2886474253","https://openalex.org/W3107686539","https://openalex.org/W2904304778","https://openalex.org/W2149479912","https://openalex.org/W2121863487","https://openalex.org/W3110042586","https://openalex.org/W2822752092","https://openalex.org/W2004001705","https://openalex.org/W2991046523","https://openalex.org/W2964990165","https://openalex.org/W2963774238","https://openalex.org/W2966348706","https://openalex.org/W2963747324","https://openalex.org/W2963308146","https://openalex.org/W2982493444","https://openalex.org/W3155542523","https://openalex.org/W2744885317","https://openalex.org/W257388195","https://openalex.org/W3136957854","https://openalex.org/W1990776012"],"abstract_inverted_index":{"This":[0],"article":[1],"considers":[2],"a":[3,23,36,100],"distributed":[4,25,37],"reinforcement":[5],"learning":[6],"problem":[7,112],"for":[8],"decentralized":[9],"linear":[10,32],"quadratic":[11],"(LQ)":[12],"control":[13],"with":[14,105,131],"partial":[15],"state":[16],"observations":[17],"and":[18,47,60,78,92,110],"local":[19,33,63],"costs.":[20],"We":[21,119],"propose":[22],"zero-order":[24,45,70],"policy":[26,43,64],"optimization":[27],"algorithm":[28],"(ZODPO)":[29],"that":[30,94,122],"learns":[31],"controllers":[34,124,130],"in":[35,66,81],"fashion,":[38],"leveraging":[39],"the":[40,55,87,95,106,111,115,123],"ideas":[41],"of":[42,90,117],"gradient,":[44],"optimization,":[46],"consensus":[48],"algorithms.":[49],"In":[50],"ZODPO,":[51],"each":[52],"agent":[53],"estimates":[54],"global":[56],"cost":[57],"by":[58],"consensus,":[59],"then":[61],"conducts":[62],"gradient":[65,71],"parallel":[67],"based":[68],"on":[69,139],"estimation.":[72],"ZODPO":[73,91,127,138],"only":[74],"requires":[75],"limited":[76],"communication":[77],"storage":[79],"even":[80],"large-scale":[82],"systems.":[83,142],"Further,":[84],"we":[85,135],"investigate":[86],"nonasymptotic":[88],"performance":[89],"show":[93,121],"sample":[96],"complexity":[97],"to":[98],"approach":[99],"stationary":[101],"point":[102],"is":[103],"polynomial":[104],"error":[107],"tolerance\u2019s":[108],"inverse":[109],"dimensions,":[113],"demonstrating":[114],"scalability":[116],"ZODPO.":[118],"also":[120],"generated":[125],"throughout":[126],"are":[128],"stabilizing":[129],"high":[132],"probability.":[133],"Last,":[134],"numerically":[136],"test":[137],"multizone":[140],"HVAC":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}