{"id":"https://openalex.org/W4310969904","doi":"https://doi.org/10.1109/iecon49645.2022.9968893","title":"Robust Parameter Estimation and Tracking through Lyapunov-based Actor-Critic Reinforcement Learning","display_name":"Robust Parameter Estimation and Tracking through Lyapunov-based Actor-Critic Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-17","ids":{"openalex":"https://openalex.org/W4310969904","doi":"https://doi.org/10.1109/iecon49645.2022.9968893"},"language":"en","primary_location":{"id":"doi:10.1109/iecon49645.2022.9968893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon49645.2022.9968893","pdf_url":null,"source":{"id":"https://openalex.org/S4363607717","display_name":"IECON 2022 \u2013 48th Annual Conference of the IEEE Industrial Electronics Society","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2022 \u2013 48th Annual Conference of the IEEE Industrial Electronics Society","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/A5024092512","display_name":"Thomas Rudolf","orcid":"https://orcid.org/0000-0002-6020-2611"},"institutions":[{"id":"https://openalex.org/I143379178","display_name":"FZI Research Center for Information Technology","ror":"https://ror.org/04kdh6x72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I143379178"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Rudolf","raw_affiliation_strings":["FZI Research Center for Information Technology,Embedded Systems and Sensors Engineering,Karlsruhe,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FZI Research Center for Information Technology,Embedded Systems and Sensors Engineering,Karlsruhe,Germany","institution_ids":["https://openalex.org/I143379178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064819266","display_name":"Joshua Ransiek","orcid":null},"institutions":[{"id":"https://openalex.org/I143379178","display_name":"FZI Research Center for Information Technology","ror":"https://ror.org/04kdh6x72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I143379178"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Joshua Ransiek","raw_affiliation_strings":["FZI Research Center for Information Technology,Embedded Systems and Sensors Engineering,Karlsruhe,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FZI Research Center for Information Technology,Embedded Systems and Sensors Engineering,Karlsruhe,Germany","institution_ids":["https://openalex.org/I143379178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090909486","display_name":"Stefan Schwab","orcid":"https://orcid.org/0000-0002-2646-7755"},"institutions":[{"id":"https://openalex.org/I143379178","display_name":"FZI Research Center for Information Technology","ror":"https://ror.org/04kdh6x72","country_code":"DE","type":"nonprofit","lineage":["https://openalex.org/I143379178"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Schwab","raw_affiliation_strings":["FZI Research Center for Information Technology,Embedded Systems and Sensors Engineering,Karlsruhe,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"FZI Research Center for Information Technology,Embedded Systems and Sensors Engineering,Karlsruhe,Germany","institution_ids":["https://openalex.org/I143379178"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040502908","display_name":"S\u00f6ren Hohmann","orcid":"https://orcid.org/0000-0002-4170-1431"},"institutions":[{"id":"https://openalex.org/I102335020","display_name":"Karlsruhe Institute of Technology","ror":"https://ror.org/04t3en479","country_code":"DE","type":"education","lineage":["https://openalex.org/I102335020","https://openalex.org/I1305996414"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Soren Hohmann","raw_affiliation_strings":["Karlsruhe Institute of Technology,Institute of Control Systems,Karlsruhe,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Karlsruhe Institute of Technology,Institute of Control Systems,Karlsruhe,Germany","institution_ids":["https://openalex.org/I102335020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4553,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91255786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.9983000159263611,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9983000159263611,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9955000281333923,"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":0.9915000200271606,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8035789132118225},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6447274684906006},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5976872444152832},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5280041694641113},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5075079798698425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.50260329246521},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.44577834010124207},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35061246156692505},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.20342645049095154},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1578693389892578},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.12996932864189148},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06544002890586853}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8035789132118225},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6447274684906006},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5976872444152832},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5280041694641113},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5075079798698425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.50260329246521},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.44577834010124207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35061246156692505},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.20342645049095154},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1578693389892578},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.12996932864189148},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06544002890586853},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iecon49645.2022.9968893","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iecon49645.2022.9968893","pdf_url":null,"source":{"id":"https://openalex.org/S4363607717","display_name":"IECON 2022 \u2013 48th Annual Conference of the IEEE Industrial Electronics Society","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IECON 2022 \u2013 48th Annual Conference of the IEEE Industrial Electronics Society","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2086161653","https://openalex.org/W2163047117","https://openalex.org/W2548796720","https://openalex.org/W2791255579","https://openalex.org/W2904246096","https://openalex.org/W2952271617","https://openalex.org/W3045059767","https://openalex.org/W3110068061","https://openalex.org/W3126886985","https://openalex.org/W3126968152","https://openalex.org/W3135455637","https://openalex.org/W3194612101","https://openalex.org/W4226047355","https://openalex.org/W4289709949","https://openalex.org/W4294555834","https://openalex.org/W6684063239","https://openalex.org/W6686634594","https://openalex.org/W6738483526","https://openalex.org/W6753691991","https://openalex.org/W6757592117","https://openalex.org/W6810971026"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2084086966","https://openalex.org/W3049728571","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"an":[3,43,90],"approach":[4],"for":[5,85,105],"parameter":[6,24,37,83,134,149],"estimation":[7,38],"of":[8,13,23,99],"nonlinear":[9,81,120,132],"systems":[10,26],"by":[11,50],"means":[12],"robust":[14,57],"maximum":[15],"entropy":[16],"offline":[17],"reinforcement":[18],"learning":[19],"(RL).":[20],"The":[21,68,123,139],"identification":[22],"variant":[25],"is":[27,48,62,70,103,127],"a":[28,51,56,94,106,130],"challenging":[29],"problem":[30],"in":[31,112],"industrial":[32],"applications.":[33],"We":[34],"address":[35],"the":[36,65,97,100,113],"on":[39,72,129],"disturbed":[40],"measurements":[41],"with":[42,116],"actor-critic":[44,59],"RL":[45,125],"agent":[46,126],"that":[47],"extended":[49],"Lyapunov":[52],"neural":[53],"network.":[54],"Accordingly,":[55],"soft":[58],"algorithm":[60],"(RSAC)":[61],"applied":[63,78],"to":[64,79,143],"parametrization":[66],"problem.":[67],"policy":[69],"learned":[71],"test":[73],"trajectories":[74],"and":[75,119],"can":[76],"be":[77],"identify":[80],"system":[82,87,148],"maps":[84],"comparable":[86],"dynamics":[88],"across":[89],"operating":[91],"range.":[92],"In":[93],"simulative":[95],"study,":[96],"performance":[98],"proposed":[101],"concept":[102],"shown":[104],"permanent":[107],"magnet":[108],"synchronous":[109],"machine":[110,133],"model":[111],"d/q-frame":[114],"formulation":[115],"current":[117],"dependent":[118],"flux":[121],"linkages.":[122],"trained":[124],"evaluated":[128],"different":[131],"set":[135],"under":[136],"noisy":[137],"measurements.":[138],"results":[140],"indicate":[141],"applicability":[142],"real-world":[144],"tasks":[145],"such":[146],"as":[147],"tracking.":[150]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}