{"id":"https://openalex.org/W4402300769","doi":"https://doi.org/10.1109/tac.2024.3455508","title":"Convergence and Sample Complexity of Policy Gradient Methods for Stabilizing Linear Systems","display_name":"Convergence and Sample Complexity of Policy Gradient Methods for Stabilizing Linear Systems","publication_year":2024,"publication_date":"2024-09-06","ids":{"openalex":"https://openalex.org/W4402300769","doi":"https://doi.org/10.1109/tac.2024.3455508"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2024.3455508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3455508","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/A5079287519","display_name":"Xingyun Fu","orcid":"https://orcid.org/0009-0003-6708-9628"},"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":"Xingyun Fu","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":3.1388,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.92085688,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"70","issue":"3","first_page":"1455","last_page":"1466"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998000264167786,"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":0.9998000264167786,"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/T11236","display_name":"Control Systems and Identification","score":0.9995999932289124,"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/T10046","display_name":"Stability and Control of Uncertain Systems","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7371805310249329},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.5426334738731384},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4666315019130707},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.46188846230506897},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.41671133041381836},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3958590030670166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3832537531852722},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3642924427986145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1279599666595459},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.08361789584159851},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.07853862643241882},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.06462424993515015}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7371805310249329},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.5426334738731384},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4666315019130707},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46188846230506897},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.41671133041381836},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3958590030670166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3832537531852722},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3642924427986145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1279599666595459},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.08361789584159851},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.07853862643241882},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.06462424993515015},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2024.3455508","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2024.3455508","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":[{"display_name":"Climate action","score":0.41999998688697815,"id":"https://metadata.un.org/sdg/13"}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W2142522228","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2194966727","https://openalex.org/W2605102758","https://openalex.org/W2822752092","https://openalex.org/W2962740831","https://openalex.org/W2963774238","https://openalex.org/W2966348706","https://openalex.org/W2979207987","https://openalex.org/W2990747716","https://openalex.org/W2995764727","https://openalex.org/W2999535065","https://openalex.org/W3044373951","https://openalex.org/W3046082844","https://openalex.org/W3046992251","https://openalex.org/W3098412154","https://openalex.org/W3114430747","https://openalex.org/W3119327948","https://openalex.org/W3128710479","https://openalex.org/W3128807880","https://openalex.org/W3137642493","https://openalex.org/W3139533914","https://openalex.org/W3155542523","https://openalex.org/W3166923021","https://openalex.org/W3206480318","https://openalex.org/W3209135762","https://openalex.org/W3213818741","https://openalex.org/W3213835390","https://openalex.org/W3214853196","https://openalex.org/W4210732025","https://openalex.org/W4239776055","https://openalex.org/W4313591116","https://openalex.org/W4376481351","https://openalex.org/W4385127973","https://openalex.org/W4391021411","https://openalex.org/W4391335360","https://openalex.org/W6602152948","https://openalex.org/W6681190598","https://openalex.org/W6682849425","https://openalex.org/W6754297394","https://openalex.org/W6756870468","https://openalex.org/W6757029329","https://openalex.org/W6762982123","https://openalex.org/W6766686101","https://openalex.org/W6767019922","https://openalex.org/W6772183843","https://openalex.org/W6779605008","https://openalex.org/W6780993544","https://openalex.org/W6781272283","https://openalex.org/W6802758289","https://openalex.org/W6810068316","https://openalex.org/W6860724725","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W1185300216","https://openalex.org/W1517908938","https://openalex.org/W2954163146","https://openalex.org/W2281834912","https://openalex.org/W1489941249","https://openalex.org/W3123492739","https://openalex.org/W2896057011","https://openalex.org/W4320486059","https://openalex.org/W2494168571","https://openalex.org/W2033096984"],"abstract_inverted_index":{"System":[0],"stabilization":[1],"via":[2],"policy":[3,57],"gradient":[4],"(PG)":[5],"methods":[6,96],"has":[7],"drawn":[8],"increasing":[9],"attention":[10],"in":[11,33,105],"both":[12],"control":[13,86],"and":[14,25,58,134],"machine":[15],"learning":[16],"communities.":[17],"In":[18],"this":[19],"article,":[20],"we":[21,67,89,126],"study":[22],"their":[23],"convergence":[24],"sample":[26,92],"complexity":[27,93],"for":[28,97,115],"stabilizing":[29,123],"linear":[30,48,85],"time-invariant":[31],"systems":[32],"terms":[34],"of":[35,38,62,83,94,109,138,144],"the":[36,56,59,63,75,80,91,106,110,117,136],"number":[37],"system":[39],"rollouts.":[40],"Our":[41],"analysis":[42],"is":[43],"built":[44],"upon":[45],"a":[46,84,102,121,142],"discounted":[47],"quadratic":[49],"regulator":[50],"(LQR)":[51],"method":[52,140],"which":[53,99],"alternatively":[54],"updates":[55],"discount":[60,76],"factor":[61,77],"LQR":[64,118],"problem.":[65],"First,":[66],"propose":[68],"an":[69],"explicit":[70],"rule":[71],"to":[72,113,129],"adaptively":[73],"adjust":[74],"by":[78],"exploring":[79],"stability":[81],"margin":[82],"policy.":[87,124],"Then,":[88],"establish":[90],"PG":[95],"stabilization,":[98],"only":[100],"adds":[101],"coefficient":[103],"logarithmic":[104],"spectral":[107],"radius":[108],"state":[111],"matrix":[112],"that":[114],"solving":[116],"problem":[119],"with":[120],"prior":[122],"Finally,":[125],"perform":[127],"simulations":[128],"validate":[130],"our":[131,139],"theoretical":[132],"findings":[133],"demonstrate":[135],"effectiveness":[137],"on":[141],"class":[143],"nonlinear":[145],"systems.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":9}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}