{"id":"https://openalex.org/W3110558707","doi":"https://doi.org/10.1109/icca51439.2020.9264402","title":"Model+Learning-based Optimal Control: an Inverted Pendulum Study","display_name":"Model+Learning-based Optimal Control: an Inverted Pendulum Study","publication_year":2020,"publication_date":"2020-10-09","ids":{"openalex":"https://openalex.org/W3110558707","doi":"https://doi.org/10.1109/icca51439.2020.9264402","mag":"3110558707"},"language":"en","primary_location":{"id":"doi:10.1109/icca51439.2020.9264402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-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/A5055979973","display_name":"Simone Baldi","orcid":"https://orcid.org/0000-0001-9752-8925"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN","NL"],"is_corresponding":true,"raw_author_name":"Simone Baldi","raw_affiliation_strings":["Delft Center for Systems and Control, TU Delft, Delft, Netherlands","School of Mathematics, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, TU Delft, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"School of Mathematics, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065139204","display_name":"Muhammad Ridho Rosa","orcid":"https://orcid.org/0000-0003-4941-0644"},"institutions":[{"id":"https://openalex.org/I862893732","display_name":"Telkom University","ror":"https://ror.org/0004wsx81","country_code":"ID","type":"education","lineage":["https://openalex.org/I862893732"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["ID","NL"],"is_corresponding":false,"raw_author_name":"Muhammad Ridho Rosa","raw_affiliation_strings":["Delft Center for Systems and Control, TU Delft, Delft, Netherlands","School of Electrical Engineering, Telkom University, Bandung, Indonesia"],"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control, TU Delft, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"School of Electrical Engineering, Telkom University, Bandung, Indonesia","institution_ids":["https://openalex.org/I862893732"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066421122","display_name":"Yuzhang Wang","orcid":"https://orcid.org/0000-0002-7690-5813"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["CN","NL"],"is_corresponding":false,"raw_author_name":"Yuzhang Wang","raw_affiliation_strings":["Center for Precision Engineering, Harbin Institute of Technology, Harbin, China","Delft Center for Systems and Control, TU Delft, Delft, Netherlands"],"affiliations":[{"raw_affiliation_string":"Center for Precision Engineering, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Delft Center for Systems and Control, TU Delft, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055979973"],"corresponding_institution_ids":["https://openalex.org/I76569877","https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":0.1445,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56141342,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"34","issue":null,"first_page":"773","last_page":"778"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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":0.9940000176429749,"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/inverted-pendulum","display_name":"Inverted pendulum","score":0.8884395360946655},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6145535111427307},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5565445423126221},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5275632739067078},{"id":"https://openalex.org/keywords/double-inverted-pendulum","display_name":"Double inverted pendulum","score":0.48187074065208435},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.45785555243492126},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3357508182525635},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.23640361428260803},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2208133339881897},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12281912565231323},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.07910540699958801}],"concepts":[{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.8884395360946655},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6145535111427307},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5565445423126221},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5275632739067078},{"id":"https://openalex.org/C102540577","wikidata":"https://www.wikidata.org/wiki/Q5300047","display_name":"Double inverted pendulum","level":4,"score":0.48187074065208435},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.45785555243492126},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3357508182525635},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.23640361428260803},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2208133339881897},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12281912565231323},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.07910540699958801},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icca51439.2020.9264402","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icca51439.2020.9264402","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 16th International Conference on Control & Automation (ICCA)","raw_type":"proceedings-article"},{"id":"pmh:oai:tudelft.nl:uuid:552ddb83-fa0d-4d9f-943f-b50c4b27b027","is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:552ddb83-fa0d-4d9f-943f-b50c4b27b027","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.6399999856948853}],"awards":[{"id":"https://openalex.org/G7084902047","display_name":null,"funder_award_id":"40257","funder_id":"https://openalex.org/F4320330150","funder_display_name":"Universitas Telkom"},{"id":"https://openalex.org/G8855562357","display_name":null,"funder_award_id":"3207012004A2","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321012","display_name":"Technische Universiteit Delft","ror":"https://ror.org/02e2c7k09"},{"id":"https://openalex.org/F4320321940","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08"},{"id":"https://openalex.org/F4320324856","display_name":"Southeast University","ror":"https://ror.org/04ct4d772"},{"id":"https://openalex.org/F4320328987","display_name":"Delft Research Centres","ror":"https://ror.org/02e2c7k09"},{"id":"https://openalex.org/F4320330150","display_name":"Universitas Telkom","ror":"https://ror.org/0004wsx81"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1529289765","https://openalex.org/W1574514837","https://openalex.org/W1966086707","https://openalex.org/W1985660326","https://openalex.org/W1995097025","https://openalex.org/W2034776151","https://openalex.org/W2039671349","https://openalex.org/W2073591687","https://openalex.org/W2075413524","https://openalex.org/W2091565802","https://openalex.org/W2101226484","https://openalex.org/W2110905106","https://openalex.org/W2116006930","https://openalex.org/W2119539930","https://openalex.org/W2129601526","https://openalex.org/W2160561608","https://openalex.org/W2312849699","https://openalex.org/W2398158765","https://openalex.org/W2539083524","https://openalex.org/W2751755465","https://openalex.org/W2953898739","https://openalex.org/W2966633400","https://openalex.org/W3103456419","https://openalex.org/W6676577771","https://openalex.org/W6712201463"],"related_works":["https://openalex.org/W2024927487","https://openalex.org/W1492838287","https://openalex.org/W2349578589","https://openalex.org/W2034778971","https://openalex.org/W2612646280","https://openalex.org/W2893549521","https://openalex.org/W2381121570","https://openalex.org/W2379721524","https://openalex.org/W2341932412","https://openalex.org/W2376869628"],"abstract_inverted_index":{"This":[0],"work":[1],"extends":[2],"and":[3,25,64,85,119],"compares":[4],"some":[5],"recent":[6],"model+learning-based":[7],"methodologies":[8],"for":[9],"optimal":[10],"control":[11,115],"with":[12],"input":[13],"saturation.":[14],"We":[15],"focus":[16],"on":[17],"two":[18],"methodologies:":[19],"a":[20,26,123],"model-based":[21],"actor-critic":[22],"(MBAC)":[23],"strategy,":[24],"nonlinear":[27,107],"policy":[28,108,116],"iteration":[29,109],"strategy.":[30],"To":[31],"evaluate":[32],"the":[33,36,43,53,58,65,71,74,90,99,103,106],"performance":[34],"of":[35],"algorithms,":[37],"these":[38],"strategies":[39],"are":[40],"applied":[41],"to":[42,98,122],"swinging":[44],"up":[45],"an":[46],"inverted":[47],"pendulum.":[48],"Numerical":[49],"simulations":[50],"show":[51],"that":[52,89,112],"neural":[54],"network":[55],"approximation":[56],"in":[57],"MBAC":[59,75],"strategy":[60],"can":[61,82],"be":[62,83],"poor,":[63],"algorithm":[66],"may":[67],"converge":[68],"far":[69],"from":[70],"optimum.":[72],"In":[73],"approach":[76,110],"neither":[77],"stabilization":[78],"nor":[79],"monotonic":[80],"convergence":[81],"guaranteed,":[84],"it":[86],"is":[87,94,117],"observed":[88],"best":[91],"value":[92],"function":[93],"not":[95],"always":[96],"corresponding":[97],"last":[100],"one.":[101],"On":[102],"other":[104],"side":[105],"guarantees":[111],"every":[113],"new":[114],"stabilizing":[118],"generally":[120],"leads":[121],"monotonically":[124],"decreasing":[125],"cost.":[126]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}