{"id":"https://openalex.org/W4382999297","doi":"https://doi.org/10.1109/tnnls.2023.3287881","title":"NN-Based Reinforcement Learning Optimal Control for Inequality-Constrained Nonlinear Discrete-Time Systems With Disturbances","display_name":"NN-Based Reinforcement Learning Optimal Control for Inequality-Constrained Nonlinear Discrete-Time Systems With Disturbances","publication_year":2023,"publication_date":"2023-07-03","ids":{"openalex":"https://openalex.org/W4382999297","doi":"https://doi.org/10.1109/tnnls.2023.3287881","pmid":"https://pubmed.ncbi.nlm.nih.gov/37399155"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2023.3287881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3287881","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100627709","display_name":"Shu Li","orcid":"https://orcid.org/0000-0002-5828-3010"},"institutions":[{"id":"https://openalex.org/I2898894","display_name":"Liaoning University of Technology","ror":"https://ror.org/05ay23762","country_code":"CN","type":"education","lineage":["https://openalex.org/I2898894"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shu Li","raw_affiliation_strings":["College of Electrical Engineering, Liaoning University of Technology, Jinzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5828-3010","affiliations":[{"raw_affiliation_string":"College of Electrical Engineering, Liaoning University of Technology, Jinzhou, China","institution_ids":["https://openalex.org/I2898894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012020883","display_name":"Liang Ding","orcid":"https://orcid.org/0000-0002-8351-5178"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Ding","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-8351-5178","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014037071","display_name":"Miao Zheng","orcid":"https://orcid.org/0009-0009-8687-6305"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miao Zheng","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0009-8687-6305","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084075146","display_name":"Z.Y. Liu","orcid":"https://orcid.org/0000-0003-0667-9053"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Liu","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-0667-9053","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101547770","display_name":"Xinyu Li","orcid":"https://orcid.org/0009-0003-7546-7473"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyu Li","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0009-0003-7546-7473","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068394600","display_name":"Huaiguang Yang","orcid":"https://orcid.org/0000-0001-6747-0988"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaiguang Yang","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0001-6747-0988","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033616367","display_name":"Haibo Gao","orcid":"https://orcid.org/0000-0002-6501-656X"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haibo Gao","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0002-6501-656X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100617483","display_name":"Zongquan Deng","orcid":"https://orcid.org/0000-0003-2432-8329"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongquan Deng","raw_affiliation_strings":["State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China"],"raw_orcid":"https://orcid.org/0000-0003-2432-8329","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.109,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.92947839,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"35","issue":"11","first_page":"15507","last_page":"15516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9442999958992004,"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":0.9442999958992004,"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/T14225","display_name":"Advanced Sensor and Control Systems","score":0.907800018787384,"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/control-theory","display_name":"Control theory (sociology)","score":0.6617237329483032},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6212685108184814},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6144111752510071},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5799782872200012},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.5715456604957581},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5505830645561218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4927728474140167},{"id":"https://openalex.org/keywords/control-lyapunov-function","display_name":"Control-Lyapunov function","score":0.48654380440711975},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.4846956729888916},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4830532670021057},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45957231521606445},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.45762383937835693},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.4354701042175293},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4245638847351074},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4092150330543518},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.32260918617248535},{"id":"https://openalex.org/keywords/lyapunov-redesign","display_name":"Lyapunov redesign","score":0.2322312295436859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13599169254302979},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12354227900505066}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6617237329483032},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6212685108184814},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6144111752510071},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5799782872200012},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.5715456604957581},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5505830645561218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4927728474140167},{"id":"https://openalex.org/C201030206","wikidata":"https://www.wikidata.org/wiki/Q5165805","display_name":"Control-Lyapunov function","level":5,"score":0.48654380440711975},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.4846956729888916},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4830532670021057},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45957231521606445},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.45762383937835693},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4354701042175293},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4245638847351074},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4092150330543518},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.32260918617248535},{"id":"https://openalex.org/C37935115","wikidata":"https://www.wikidata.org/wiki/Q6707085","display_name":"Lyapunov redesign","level":4,"score":0.2322312295436859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13599169254302979},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12354227900505066},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2023.3287881","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2023.3287881","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:37399155","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37399155","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1983615708","display_name":null,"funder_award_id":"91948202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3594036202","display_name":null,"funder_award_id":"62203198","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G387971928","display_name":null,"funder_award_id":"B07018","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"},{"id":"https://openalex.org/G5383534787","display_name":null,"funder_award_id":"51521003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5442250454","display_name":null,"funder_award_id":"52205011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G852853916","display_name":null,"funder_award_id":"HIT.BRETIV.201903","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1517236425","https://openalex.org/W1978956894","https://openalex.org/W1986024064","https://openalex.org/W2002260889","https://openalex.org/W2010699465","https://openalex.org/W2019478222","https://openalex.org/W2026276545","https://openalex.org/W2034214945","https://openalex.org/W2040622182","https://openalex.org/W2062373349","https://openalex.org/W2077195478","https://openalex.org/W2078977470","https://openalex.org/W2113442785","https://openalex.org/W2115249980","https://openalex.org/W2117945258","https://openalex.org/W2121570671","https://openalex.org/W2139704022","https://openalex.org/W2146487916","https://openalex.org/W2151858664","https://openalex.org/W2156216606","https://openalex.org/W2160561608","https://openalex.org/W2167038379","https://openalex.org/W2214816543","https://openalex.org/W2299109138","https://openalex.org/W2476385022","https://openalex.org/W2484646121","https://openalex.org/W2522467183","https://openalex.org/W2563378438","https://openalex.org/W2765910425","https://openalex.org/W2780814805","https://openalex.org/W2790630269","https://openalex.org/W2793996673","https://openalex.org/W2809883483","https://openalex.org/W2897039614","https://openalex.org/W2912259603","https://openalex.org/W2921198348","https://openalex.org/W2980011510","https://openalex.org/W2996568167","https://openalex.org/W3200288111","https://openalex.org/W3205058525","https://openalex.org/W4200008856","https://openalex.org/W4220807181","https://openalex.org/W4248204876","https://openalex.org/W4295046613","https://openalex.org/W4298300677","https://openalex.org/W4299935191","https://openalex.org/W4300885720","https://openalex.org/W4309763124","https://openalex.org/W4313146255","https://openalex.org/W4319302786","https://openalex.org/W4321487798","https://openalex.org/W4362474446","https://openalex.org/W4366112290","https://openalex.org/W4379382524"],"related_works":["https://openalex.org/W3217133416","https://openalex.org/W2349796700","https://openalex.org/W1970635650","https://openalex.org/W2126112326","https://openalex.org/W2475132469","https://openalex.org/W1976574339","https://openalex.org/W2766646824","https://openalex.org/W1996957550","https://openalex.org/W1979297933","https://openalex.org/W2588600327"],"abstract_inverted_index":{"Based":[0],"on":[1],"actor-critic":[2],"neural":[3],"networks":[4],"(NNs),":[5],"an":[6,18,76],"optimal":[7,70,84],"controller":[8],"is":[9,73,90,118],"proposed":[10],"for":[11],"solving":[12],"the":[13,29,33,38,42,46,57,63,68,80,83,93,100,112,115],"constrained":[14,69],"control":[15,30,71,85,101,116],"problem":[16,72],"of":[17,41,114],"affine":[19],"nonlinear":[20],"discrete-time":[21],"system":[22],"with":[23],"disturbances.":[24],"The":[25],"actor":[26],"NNs":[27,35],"provide":[28],"signals":[31,102],"and":[32,54,66,87],"critic":[34],"work":[36],"as":[37],"performance":[39],"indicators":[40],"controller.":[43],"By":[44],"converting":[45],"original":[47],"state":[48,55],"constraints":[49,53],"into":[50,62,75],"new":[51],"input":[52,86],"constraints,":[56],"penalty":[58],"functions":[59],"are":[60,103],"introduced":[61],"cost":[64],"function,":[65],"then":[67],"transformed":[74],"unconstrained":[77],"one.":[78],"Further,":[79],"relationship":[81],"between":[82],"worst-case":[88],"disturbance":[89],"obtained":[91],"using":[92,124],"Game":[94],"theory.":[95],"With":[96],"Lyapunov":[97],"stability":[98],"theory,":[99],"ensured":[104],"to":[105],"be":[106],"uniformly":[107],"ultimately":[108],"bounded":[109],"(UUB).":[110],"Finally,":[111],"effectiveness":[113],"algorithms":[117],"tested":[119],"through":[120],"a":[121,125],"numeral":[122],"simulation":[123],"third-order":[126],"dynamic":[127],"system.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}