{"id":"https://openalex.org/W4414008171","doi":"https://doi.org/10.1109/tsmc.2025.3604873","title":"Data-Based Inverse Reinforcement Learning for Nonlinear Systems With Control Constraints","display_name":"Data-Based Inverse Reinforcement Learning for Nonlinear Systems With Control Constraints","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4414008171","doi":"https://doi.org/10.1109/tsmc.2025.3604873"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2025.3604873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3604873","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Transactions on Systems, Man, and Cybernetics: Systems","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/A5020669784","display_name":"Huaipin Zhang","orcid":"https://orcid.org/0000-0001-6405-1382"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huaipin Zhang","raw_affiliation_strings":["Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069593829","display_name":"Weijie You","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijie You","raw_affiliation_strings":["Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434523","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0001-8045-2549"},"institutions":[{"id":"https://openalex.org/I137056471","display_name":"Nanjing University of Finance and Economics","ror":"https://ror.org/031y8am81","country_code":"CN","type":"education","lineage":["https://openalex.org/I137056471"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Nanjing University of Finance and Economics, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Nanjing University of Finance and Economics, Nanjing, China","institution_ids":["https://openalex.org/I137056471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055548778","display_name":"Lei Ding","orcid":"https://orcid.org/0000-0003-3555-1411"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Ding","raw_affiliation_strings":["Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100727487","display_name":"Dong Yue","orcid":"https://orcid.org/0000-0001-7810-9338"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yue","raw_affiliation_strings":["Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5020669784"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28613595,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9783999919891357,"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":0.9783999919891357,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9706000089645386,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9629999995231628,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6501545310020447},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6424808502197266},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5913536548614502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5460612177848816},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4971466362476349},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4917745888233185},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.484096884727478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3702850043773651},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30498552322387695},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15379923582077026},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0972524881362915},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06800097227096558}],"concepts":[{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6501545310020447},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6424808502197266},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5913536548614502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5460612177848816},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4971466362476349},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4917745888233185},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.484096884727478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3702850043773651},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30498552322387695},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15379923582077026},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0972524881362915},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06800097227096558},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2025.3604873","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3604873","pdf_url":null,"source":{"id":"https://openalex.org/S4210209078","display_name":"IEEE Transactions on Systems Man and Cybernetics Systems","issn_l":"2168-2216","issn":["2168-2216","2168-2232"],"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 Transactions on Systems, Man, and Cybernetics: Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G493782230","display_name":null,"funder_award_id":"62203208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7937144976","display_name":null,"funder_award_id":"62573238","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"an":[3],"online":[4],"data-based":[5,66,85],"inverse":[6],"reinforcement":[7],"learning":[8],"(IRL)":[9],"scheme":[10],"to":[11,49,76,88,131],"solve":[12],"optimal":[13,54,61],"control":[14,20,42,55,62],"problem":[15,56],"for":[16],"nonlinear":[17],"systems":[18],"with":[19,41],"constraints,":[21],"in":[22],"which":[23],"the":[24,32,51,78,90,96,101,116,120,133,136],"unknown":[25,91],"reward":[26,92,105],"functions":[27],"are":[28],"recovered":[29],"based":[30],"on":[31],"systems\u2019":[33],"demonstrated":[34,108],"state":[35,109],"and":[36,94,104,110],"input":[37,111],"data.":[38,112],"To":[39],"deal":[40],"constraint,":[43],"we":[44,82],"introduce":[45],"a":[46,58,65,84],"saturation":[47],"function":[48,93,103,106],"formulate":[50],"original":[52],"constrained":[53],"into":[57],"new":[59],"unconstrained":[60],"problem.":[63],"Then":[64],"identifier":[67],"using":[68,107],"neural":[69],"network":[70],"(NN)":[71],"approximation":[72],"technique":[73],"is":[74,124,129],"designed":[75],"estimate":[77],"system\u2019s":[79],"dynamics.":[80],"Subsequently,":[81],"develop":[83],"IRL":[86],"approach":[87],"learn":[89],"establish":[95],"weight":[97,121],"tuning":[98],"law":[99],"of":[100,115,119,135],"value":[102],"The":[113],"proof":[114],"uniform":[117],"boundedness":[118],"estimation":[122],"error":[123],"presented.":[125],"A":[126],"simulation":[127],"example":[128],"provided":[130],"verify":[132],"effectiveness":[134],"proposed":[137],"approach.":[138]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}