{"id":"https://openalex.org/W4285139567","doi":"https://doi.org/10.1109/lcsys.2022.3188180","title":"Computing Stabilizing Feedback Gains via a Model-Free Policy Gradient Method","display_name":"Computing Stabilizing Feedback Gains via a Model-Free Policy Gradient Method","publication_year":2022,"publication_date":"2022-07-04","ids":{"openalex":"https://openalex.org/W4285139567","doi":"https://doi.org/10.1109/lcsys.2022.3188180"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2022.3188180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2022.3188180","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/A5012854172","display_name":"Ibrahim K. Ozaslan","orcid":"https://orcid.org/0000-0001-9974-4998"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ibrahim K. Ozaslan","raw_affiliation_strings":["Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California Los Angeles, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-9974-4998","affiliations":[{"raw_affiliation_string":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047399398","display_name":"Hesameddin Mohammadi","orcid":"https://orcid.org/0000-0003-3030-1536"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hesameddin Mohammadi","raw_affiliation_strings":["Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California Los Angeles, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-3030-1536","affiliations":[{"raw_affiliation_string":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087790067","display_name":"Mihailo R. Jovanovi\u0107","orcid":"https://orcid.org/0000-0002-4181-2924"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mihailo R. Jovanovic","raw_affiliation_strings":["Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California Los Angeles, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4181-2924","affiliations":[{"raw_affiliation_string":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012854172"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.8324,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77439122,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":"7","issue":null,"first_page":"407","last_page":"412"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9983999729156494,"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"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9973000288009644,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convexity","display_name":"Convexity","score":0.6142527461051941},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.58962082862854},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.583164632320404},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.582661509513855},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5361447334289551},{"id":"https://openalex.org/keywords/relaxation","display_name":"Relaxation (psychology)","score":0.5231857895851135},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5152474045753479},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.450111985206604},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4354848861694336},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4328746795654297},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.287123441696167},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.12299126386642456}],"concepts":[{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.6142527461051941},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.58962082862854},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.583164632320404},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.582661509513855},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5361447334289551},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.5231857895851135},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5152474045753479},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.450111985206604},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4354848861694336},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4328746795654297},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.287123441696167},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.12299126386642456},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2022.3188180","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2022.3188180","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":[],"awards":[{"id":"https://openalex.org/G1136593804","display_name":null,"funder_award_id":"ECCS-1809833","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3547737668","display_name":null,"funder_award_id":"ECCS-1708906","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W116296291","https://openalex.org/W1980183459","https://openalex.org/W2056241376","https://openalex.org/W2066686615","https://openalex.org/W2403559170","https://openalex.org/W2904304778","https://openalex.org/W2962872206","https://openalex.org/W3011908139","https://openalex.org/W3046017196","https://openalex.org/W3046082844","https://openalex.org/W3046992251","https://openalex.org/W3102961917","https://openalex.org/W3119327948","https://openalex.org/W3166923021","https://openalex.org/W3186548793","https://openalex.org/W3206480318","https://openalex.org/W3209135762","https://openalex.org/W4250954493","https://openalex.org/W4253020970","https://openalex.org/W6637967152","https://openalex.org/W6754297394","https://openalex.org/W6756870468","https://openalex.org/W6757029329","https://openalex.org/W6772183843","https://openalex.org/W6802758289","https://openalex.org/W6810392763"],"related_works":["https://openalex.org/W1964872188","https://openalex.org/W2187391117","https://openalex.org/W1981809986","https://openalex.org/W2949367465","https://openalex.org/W2587048717","https://openalex.org/W4235203617","https://openalex.org/W2006359264","https://openalex.org/W3029201158","https://openalex.org/W4794847","https://openalex.org/W2056357792"],"abstract_inverted_index":{"In":[0],"spite":[1],"of":[2,5,47,59,66,79,151],"the":[3,16,22,45,72,77,83,95,98,104,115,127,134,148],"lack":[4],"convexity,":[6],"convergence":[7],"and":[8,50,110,143],"sample":[9],"complexity":[10],"properties":[11],"were":[12],"recently":[13],"established":[14],"for":[15,70,82,94],"random":[17],"search":[18],"method":[19],"applied":[20],"to":[21,76],"linear":[23,86],"quadratic":[24],"regulator":[25],"(LQR)":[26],"problem.":[27],"Since":[28],"policy":[29,107],"gradient":[30,108],"approaches":[31],"require":[32],"an":[33],"initial":[34],"stabilizing":[35,53,80,92],"controller,":[36],"we":[37,131],"propose":[38],"a":[39,52,56,64,91,140],"model-free":[40],"algorithm":[41,62],"that":[42,133],"searches":[43],"over":[44],"set":[46,78],"state-feedback":[48],"gains":[49],"returns":[51],"controller":[54,93,105],"in":[55,114],"finite":[57],"number":[58,150],"iterations.":[60,123,152],"Our":[61],"involves":[63],"sequence":[65],"relaxed":[67,96],"LQR":[68,116],"problems":[69],"which":[71],"associated":[73],"domains":[74],"converge":[75],"controllers":[81],"original":[84],"continuous-time":[85],"time-invariant":[87],"system.":[88],"Starting":[89],"from":[90],"problem,":[97],"proposed":[99],"approach":[100],"alternates":[101],"between":[102],"updating":[103],"via":[106],"iterations":[109],"decreasing":[111],"relaxation":[112,128],"parameter":[113,129],"cost":[117,135],"while":[118],"preserving":[119],"stability":[120],"at":[121],"all":[122],"By":[124],"properly":[125],"tuning":[126],"updates":[130],"ensure":[132],"values":[136],"do":[137],"not":[138],"exceed":[139],"uniform":[141],"threshold":[142],"establish":[144],"computable":[145],"bounds":[146],"on":[147],"total":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}