{"id":"https://openalex.org/W4280599139","doi":"https://doi.org/10.1080/00207721.2022.2074568","title":"Reinforcement learning-based optimised control for a class of second-order nonlinear dynamic systems","display_name":"Reinforcement learning-based optimised control for a class of second-order nonlinear dynamic systems","publication_year":2022,"publication_date":"2022-05-16","ids":{"openalex":"https://openalex.org/W4280599139","doi":"https://doi.org/10.1080/00207721.2022.2074568"},"language":"en","primary_location":{"id":"doi:10.1080/00207721.2022.2074568","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207721.2022.2074568","pdf_url":null,"source":{"id":"https://openalex.org/S129640837","display_name":"International Journal of Systems Science","issn_l":"0020-7721","issn":["0020-7721","1464-5319"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Systems Science","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/A5100744772","display_name":"Bin Li","orcid":"https://orcid.org/0000-0002-4028-0938"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin Li","raw_affiliation_strings":["School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences), Jinan, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences), Jinan, People's Republic of China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059125663","display_name":"Xue Yang","orcid":"https://orcid.org/0000-0002-6193-2202"},"institutions":[{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue Yang","raw_affiliation_strings":["School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences), Jinan, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences), Jinan, People's Republic of China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067220580","display_name":"Ranran Zhou","orcid":"https://orcid.org/0000-0002-9942-2902"},"institutions":[{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ranran Zhou","raw_affiliation_strings":["School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences), Jinan, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences), Jinan, People's Republic of China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063205336","display_name":"Guoxing Wen","orcid":"https://orcid.org/0000-0002-6392-5989"},"institutions":[{"id":"https://openalex.org/I152269853","display_name":"Qilu University of Technology","ror":"https://ror.org/04hyzq608","country_code":"CN","type":"education","lineage":["https://openalex.org/I152269853"]},{"id":"https://openalex.org/I4210142748","display_name":"Shandong Academy of Sciences","ror":"https://ror.org/04y8d6y55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I151013683","display_name":"Binzhou University","ror":"https://ror.org/05frpfj73","country_code":"CN","type":"education","lineage":["https://openalex.org/I151013683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoxing Wen","raw_affiliation_strings":["College of Science, Binzhou University, Binzhou, People's Republic of China","School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences), Jinan, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"College of Science, Binzhou University, Binzhou, People's Republic of China","institution_ids":["https://openalex.org/I151013683"]},{"raw_affiliation_string":"School of Mathematics and Statistics, Qilu University of Technology (Shandong Academy of Sciences), Jinan, People's Republic of China","institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100744772"],"corresponding_institution_ids":["https://openalex.org/I152269853","https://openalex.org/I4210142748"],"apc_list":null,"apc_paid":null,"fwci":1.5036,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84175294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"53","issue":"15","first_page":"3154","last_page":"3164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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":1.0,"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":0.9911999702453613,"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/T12047","display_name":"Viral Infections and Vectors","score":0.9775999784469604,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/hamilton\u2013jacobi\u2013bellman-equation","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","score":0.8535537123680115},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8042775988578796},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7156611680984497},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.7011798024177551},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.539989709854126},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.48592105507850647},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.47155117988586426},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.470612108707428},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.45065921545028687},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.4441899061203003},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43644893169403076},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.41841909289360046},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3554818332195282},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18386182188987732}],"concepts":[{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.8535537123680115},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8042775988578796},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7156611680984497},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.7011798024177551},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.539989709854126},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.48592105507850647},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.47155117988586426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.470612108707428},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.45065921545028687},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.4441899061203003},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43644893169403076},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.41841909289360046},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3554818332195282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18386182188987732},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","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":2,"locations":[{"id":"doi:10.1080/00207721.2022.2074568","is_oa":false,"landing_page_url":"https://doi.org/10.1080/00207721.2022.2074568","pdf_url":null,"source":{"id":"https://openalex.org/S129640837","display_name":"International Journal of Systems Science","issn_l":"0020-7721","issn":["0020-7721","1464-5319"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Systems Science","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:taf:tsysxx:v:53:y:2022:i:15:p:3154-3164","is_oa":false,"landing_page_url":"http://hdl.handle.net/10.1080/00207721.2022.2074568","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2766372719","display_name":null,"funder_award_id":"ZR2020MF097","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"},{"id":"https://openalex.org/G6390619641","display_name":null,"funder_award_id":"61973185","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8866375341","display_name":null,"funder_award_id":"62073045","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"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1919998456","https://openalex.org/W1969959431","https://openalex.org/W1974103200","https://openalex.org/W1983523797","https://openalex.org/W1995168508","https://openalex.org/W2032251775","https://openalex.org/W2065529863","https://openalex.org/W2107674817","https://openalex.org/W2113501460","https://openalex.org/W2153890087","https://openalex.org/W2167287735","https://openalex.org/W2262108890","https://openalex.org/W2334591577","https://openalex.org/W2484646121","https://openalex.org/W2514286655","https://openalex.org/W2530077971","https://openalex.org/W2765847625","https://openalex.org/W2809391642","https://openalex.org/W2811002385","https://openalex.org/W2887519063","https://openalex.org/W2908542426","https://openalex.org/W2912259603","https://openalex.org/W2990777660","https://openalex.org/W3008524635","https://openalex.org/W3031327593","https://openalex.org/W3041284915","https://openalex.org/W3197005866","https://openalex.org/W4206759694","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2032834442","https://openalex.org/W3153900688","https://openalex.org/W2115544975","https://openalex.org/W2902017027","https://openalex.org/W1654696814","https://openalex.org/W4291598237","https://openalex.org/W4239477580","https://openalex.org/W2766998270","https://openalex.org/W4255265352","https://openalex.org/W3168988147"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,74],"optimised":[4,48,57],"tracking":[5],"control":[6,49,119,129,151],"scheme":[7],"based":[8,84],"on":[9,85],"reinforcement":[10],"learning":[11],"(RL)":[12],"for":[13,143],"a":[14,101],"class":[15],"of":[16,40,69,100,112,138],"second-order":[17,31],"nonlinear":[18,145],"systems":[19],"with":[20,108,125],"unknown":[21],"dynamics.":[22],"Different":[23],"from":[24,96],"the":[25,30,56,67,86,90,97,109,118,126,136,144,148,155],"first-order":[26],"dynamic":[27],"system":[28],"control,":[29,58],"case":[32],"is":[33,63,76],"required":[34],"to":[35,52,65,123],"synchronously":[36],"steer":[37],"two":[38],"variables":[39],"position":[41],"and":[42,72,82,141,164],"velocity,":[43],"hence":[44],"it":[45,115,132],"makes":[46],"this":[47],"more":[50],"challenging":[51],"accomplish.":[53],"To":[54],"achieve":[55],"first,":[59],"neural":[60],"network":[61],"(NN)":[62],"employed":[64],"approximate":[66],"solution":[68],"Hamilton\u2013Jacobi\u2013Bellman":[70],"(HJB),":[71],"then":[73],"RL":[75,91],"performed":[77],"by":[78,161],"constructing":[79],"both":[80],"critic":[81],"actor":[83],"NN":[87],"approximation.":[88],"Since":[89],"training":[92],"laws":[93],"are":[94,159],"derived":[95],"negative":[98],"gradient":[99],"simple":[102,122],"positive":[103],"function":[104],"generated":[105],"in":[106],"accordance":[107],"partial":[110],"derivative":[111],"HJB":[113],"equation,":[114],"can":[116,133,153],"make":[117],"algorithm":[120],"significantly":[121],"compare":[124],"existing":[127],"optimal":[128],"methods.":[130],"Meanwhile,":[131],"also":[134],"release":[135],"condition":[137],"persistence":[139],"excitation":[140],"compensate":[142],"uncertainty.":[146],"Finally,":[147],"proposed":[149],"adaptive":[150],"method":[152],"guarantee":[154],"desired":[156],"results":[157],"that":[158],"demonstrated":[160],"theorem,":[162],"proof":[163],"simulation.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}