{"id":"https://openalex.org/W3019868075","doi":"https://doi.org/10.1109/lcsys.2020.2989683","title":"Global Convergence of Policy Gradient Algorithms for Indefinite Least Squares Stationary Optimal Control","display_name":"Global Convergence of Policy Gradient Algorithms for Indefinite Least Squares Stationary Optimal Control","publication_year":2020,"publication_date":"2020-04-22","ids":{"openalex":"https://openalex.org/W3019868075","doi":"https://doi.org/10.1109/lcsys.2020.2989683","mag":"3019868075"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2020.2989683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2020.2989683","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","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/A5101906729","display_name":"Jingjing Bu","orcid":"https://orcid.org/0000-0002-0098-5212"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingjing Bu","raw_affiliation_strings":["University of Washington, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040511603","display_name":"Mehran Mesbahi","orcid":"https://orcid.org/0000-0001-6972-6588"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I58610484","display_name":"Seattle University","ror":"https://ror.org/02jqc0m91","country_code":"US","type":"education","lineage":["https://openalex.org/I58610484"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehran Mesbahi","raw_affiliation_strings":["University of Washington, Seattle, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, USA","institution_ids":["https://openalex.org/I201448701","https://openalex.org/I58610484"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6907,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.75532609,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"4","issue":"3","first_page":"638","last_page":"643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9998999834060669,"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/T10545","display_name":"Optimization and Variational Analysis","score":0.9918000102043152,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9896000027656555,"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/convergence","display_name":"Convergence (economics)","score":0.7107620239257812},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.6671245694160461},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5885503888130188},{"id":"https://openalex.org/keywords/least-squares-function-approximation","display_name":"Least-squares function approximation","score":0.5710815787315369},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5707129240036011},{"id":"https://openalex.org/keywords/stationary-point","display_name":"Stationary point","score":0.5361537933349609},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.4797995388507843},{"id":"https://openalex.org/keywords/recursive-least-squares-filter","display_name":"Recursive least squares filter","score":0.4707014560699463},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.46897849440574646},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4480587840080261},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4202510118484497},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.42022061347961426},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.364744633436203},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3446922302246094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.2643698453903198},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20542383193969727},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10009914636611938}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7107620239257812},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.6671245694160461},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5885503888130188},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.5710815787315369},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5707129240036011},{"id":"https://openalex.org/C189237950","wikidata":"https://www.wikidata.org/wiki/Q2500758","display_name":"Stationary point","level":2,"score":0.5361537933349609},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.4797995388507843},{"id":"https://openalex.org/C145249878","wikidata":"https://www.wikidata.org/wiki/Q2835868","display_name":"Recursive least squares filter","level":3,"score":0.4707014560699463},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.46897849440574646},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4480587840080261},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4202510118484497},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42022061347961426},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.364744633436203},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3446922302246094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2643698453903198},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20542383193969727},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10009914636611938},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0},{"id":"https://openalex.org/C102248274","wikidata":"https://www.wikidata.org/wiki/Q168388","display_name":"Adaptive filter","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2020.2989683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2020.2989683","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4795485331","display_name":null,"funder_award_id":"FA8650-18-2-7836","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G768934453","display_name":null,"funder_award_id":"FA9550-16-1-0022","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W181733065","https://openalex.org/W1600349401","https://openalex.org/W1616818660","https://openalex.org/W1804910891","https://openalex.org/W1992208280","https://openalex.org/W2002357820","https://openalex.org/W2011866373","https://openalex.org/W2087063454","https://openalex.org/W2097415784","https://openalex.org/W2098432798","https://openalex.org/W2115832833","https://openalex.org/W2148439597","https://openalex.org/W2152161277","https://openalex.org/W2165726932","https://openalex.org/W2480611454","https://openalex.org/W2595897327","https://openalex.org/W2886474253","https://openalex.org/W2903410452","https://openalex.org/W2963774238","https://openalex.org/W2984078320","https://openalex.org/W3035578948","https://openalex.org/W4388319978","https://openalex.org/W6682168952","https://openalex.org/W6754297394","https://openalex.org/W6766686101","https://openalex.org/W6770404689","https://openalex.org/W6780383567"],"related_works":["https://openalex.org/W1525886636","https://openalex.org/W1602531054","https://openalex.org/W4242740646","https://openalex.org/W4239999152","https://openalex.org/W2973191244","https://openalex.org/W2145213470","https://openalex.org/W2038428770","https://openalex.org/W1972943862","https://openalex.org/W4291198056","https://openalex.org/W2951738848"],"abstract_inverted_index":{"We":[0,41],"consider":[1],"policy":[2],"gradient":[3,49],"algorithms":[4],"for":[5,53],"the":[6,43],"indefinite":[7,17,57],"least":[8,58],"squares":[9,59],"stationary":[10],"optimal":[11],"control,":[12],"e.g.,":[13],"linear-quadratic-regulator":[14],"(LQR)":[15],"with":[16,32],"state":[18],"and":[19,50],"input":[20],"penalization":[21],"matrices.":[22],"Such":[23],"a":[24],"setup":[25],"has":[26],"important":[27],"applications":[28],"in":[29],"control":[30],"design":[31],"conflicting":[33],"objectives,":[34],"such":[35],"as":[36],"linear":[37],"quadratic":[38],"dynamic":[39],"games.":[40],"show":[42],"global":[44],"convergence":[45],"of":[46,56],"gradient,":[47],"natural":[48],"quasi-Newton":[51],"policies":[52],"this":[54],"class":[55],"problems.":[60]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}