{"id":"https://openalex.org/W4315471854","doi":"https://doi.org/10.1109/cdc51059.2022.9992367","title":"A Homotopic Approach to Policy Gradients for Linear Quadratic Regulators with Nonlinear Controls","display_name":"A Homotopic Approach to Policy Gradients for Linear Quadratic Regulators with Nonlinear Controls","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4315471854","doi":"https://doi.org/10.1109/cdc51059.2022.9992367"},"language":"en","primary_location":{"id":"pmh:oai:arpi.unipi.it:11568/1169226","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1169226","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"type":"article","indexed_in":[],"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/A5032427290","display_name":"Craig Xu Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chen C. X.","raw_affiliation_strings":["Department of Mathematics, Duke University, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Duke University, United States","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046714529","display_name":"Andr\u00e9a Agazzi","orcid":"https://orcid.org/0000-0001-7498-6034"},"institutions":[{"id":"https://openalex.org/I108290504","display_name":"University of Pisa","ror":"https://ror.org/03ad39j10","country_code":"IT","type":"education","lineage":["https://openalex.org/I108290504"]},{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["IT","US"],"is_corresponding":false,"raw_author_name":"Agazzi A.","raw_affiliation_strings":["Department of Mathematics, Duke University, United States","Department of Mathematics, University of Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Duke University, United States","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Department of Mathematics, University of Pisa, Italy","institution_ids":["https://openalex.org/I108290504"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032427290"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":0.2774,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64842673,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9921000003814697,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9894999861717224,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/counterexample","display_name":"Counterexample","score":0.6816679835319519},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6801014542579651},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.6372025609016418},{"id":"https://openalex.org/keywords/lipschitz-continuity","display_name":"Lipschitz continuity","score":0.5793827772140503},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5320262312889099},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5252879858016968},{"id":"https://openalex.org/keywords/piecewise-linear-function","display_name":"Piecewise linear function","score":0.48354578018188477},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4794713258743286},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.43780988454818726},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4289674758911133},{"id":"https://openalex.org/keywords/maxima-and-minima","display_name":"Maxima and minima","score":0.4129529595375061},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.37493908405303955},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.25157085061073303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.23184752464294434},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.14610174298286438},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.11354866623878479},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.05817416310310364}],"concepts":[{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.6816679835319519},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6801014542579651},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.6372025609016418},{"id":"https://openalex.org/C22324862","wikidata":"https://www.wikidata.org/wiki/Q652707","display_name":"Lipschitz continuity","level":2,"score":0.5793827772140503},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5320262312889099},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5252879858016968},{"id":"https://openalex.org/C17095337","wikidata":"https://www.wikidata.org/wiki/Q2375229","display_name":"Piecewise linear function","level":2,"score":0.48354578018188477},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4794713258743286},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.43780988454818726},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4289674758911133},{"id":"https://openalex.org/C186633575","wikidata":"https://www.wikidata.org/wiki/Q845060","display_name":"Maxima and minima","level":2,"score":0.4129529595375061},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.37493908405303955},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.25157085061073303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.23184752464294434},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.14610174298286438},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.11354866623878479},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.05817416310310364},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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},{"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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":"pmh:oai:arpi.unipi.it:11568/1169226","is_oa":false,"landing_page_url":"https://hdl.handle.net/11568/1169226","pdf_url":null,"source":{"id":"https://openalex.org/S4377196265","display_name":"CINECA IRIS Institutial research information system (University of Pisa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I108290504","host_organization_name":"University of Pisa","host_organization_lineage":["https://openalex.org/I108290504"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6399999856948853}],"awards":[],"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":22,"referenced_works":["https://openalex.org/W177930832","https://openalex.org/W1583837637","https://openalex.org/W2155027007","https://openalex.org/W2194966727","https://openalex.org/W2257979135","https://openalex.org/W2529970964","https://openalex.org/W2598912124","https://openalex.org/W2612690371","https://openalex.org/W2736601468","https://openalex.org/W2747329762","https://openalex.org/W2902907165","https://openalex.org/W2907537824","https://openalex.org/W2963411833","https://openalex.org/W2963774238","https://openalex.org/W2966348706","https://openalex.org/W2982316857","https://openalex.org/W3158594576","https://openalex.org/W3173515307","https://openalex.org/W3206321238","https://openalex.org/W4212774754","https://openalex.org/W4226119189","https://openalex.org/W4315471854"],"related_works":["https://openalex.org/W2349952486","https://openalex.org/W1489260687","https://openalex.org/W2775700832","https://openalex.org/W2587222766","https://openalex.org/W3204670144","https://openalex.org/W2163101548","https://openalex.org/W1988934358","https://openalex.org/W4389574038","https://openalex.org/W1492351406","https://openalex.org/W3133655088"],"abstract_inverted_index":{"We":[0,36,84],"study":[1],"the":[2,16,24,31,44,56,79,97,101],"convergence":[3],"of":[4,33,55,78,91,100,111],"deterministic":[5],"policy":[6,45,57,81,92],"gradient":[7,58,82,93],"algorithms":[8],"in":[9,52],"continuous":[10],"state":[11],"and":[12],"action":[13],"space":[14,26],"for":[15,107],"prototypical":[17],"Linear":[18,103],"Quadratic":[19,104],"Regulator":[20,105],"(LQR)":[21],"problem":[22,106],"when":[23],"search":[25],"is":[27],"not":[28],"limited":[29],"to":[30,47,96],"family":[32],"linear":[34,49],"policies.":[35,114],"first":[37],"provide":[38],"a":[39,66,73,108],"counterexample":[40],"showing":[41],"that":[42,69,87],"extending":[43],"class":[46,110],"piecewise":[48],"functions":[50],"results":[51],"local":[53],"minima":[54],"algorithm.":[59,83],"To":[60],"solve":[61],"this":[62,88],"problem,":[63],"we":[64],"develop":[65],"new":[67],"approach":[68],"involves":[70],"sequentially":[71],"increasing":[72],"discount":[74],"factor":[75],"between":[76],"iterations":[77],"original":[80],"finally":[85],"prove":[86],"homotopic":[89],"variant":[90],"methods":[94],"converges":[95],"global":[98],"optimum":[99],"undiscounted":[102],"large":[109],"Lipschitz,":[112],"non-linear":[113]},"counts_by_year":[{"year":2022,"cited_by_count":2}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}