{"id":"https://openalex.org/W4390829281","doi":"https://doi.org/10.1109/tsmc.2023.3344883","title":"Reinforcement Learning Controller Design for Discrete-Time-Constrained Nonlinear Systems With Weight Initialization Method","display_name":"Reinforcement Learning Controller Design for Discrete-Time-Constrained Nonlinear Systems With Weight Initialization Method","publication_year":2024,"publication_date":"2024-01-12","ids":{"openalex":"https://openalex.org/W4390829281","doi":"https://doi.org/10.1109/tsmc.2023.3344883"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2023.3344883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2023.3344883","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/A5058905701","display_name":"Jiahui Xu","orcid":"https://orcid.org/0000-0002-4058-0447"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Xu","raw_affiliation_strings":["Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4058-0447","affiliations":[{"raw_affiliation_string":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100777024","display_name":"Jingcheng Wang","orcid":"https://orcid.org/0000-0002-4277-1263"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingcheng Wang","raw_affiliation_strings":["Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4277-1263","affiliations":[{"raw_affiliation_string":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000872966","display_name":"Yanjiu Zhong","orcid":"https://orcid.org/0000-0002-4361-9378"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjiu Zhong","raw_affiliation_strings":["Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4361-9378","affiliations":[{"raw_affiliation_string":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018604914","display_name":"Jun Rao","orcid":"https://orcid.org/0000-0002-7467-4898"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Rao","raw_affiliation_strings":["Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7467-4898","affiliations":[{"raw_affiliation_string":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087893108","display_name":"Shunyu Wu","orcid":"https://orcid.org/0000-0001-9856-2148"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shunyu Wu","raw_affiliation_strings":["Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9856-2148","affiliations":[{"raw_affiliation_string":"Department of Automation, Key Laboratory of System Control and Information Processing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":2.5009,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89533213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"54","issue":"4","first_page":"2368","last_page":"2378"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9968000054359436,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965000152587891,"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":0.8458150029182434},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.825896143913269},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6996044516563416},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.67549729347229},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6670803427696228},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6305893659591675},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5330003499984741},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.532166600227356},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.4668021500110626},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4234687387943268},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2932925820350647},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.2861378788948059},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20365557074546814},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17961275577545166},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12634512782096863}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8458150029182434},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.825896143913269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6996044516563416},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.67549729347229},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6670803427696228},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6305893659591675},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5330003499984741},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.532166600227356},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.4668021500110626},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4234687387943268},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2932925820350647},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2861378788948059},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20365557074546814},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17961275577545166},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12634512782096863},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/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/tsmc.2023.3344883","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2023.3344883","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/G4341435642","display_name":null,"funder_award_id":"62273234","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W241118364","https://openalex.org/W1522301498","https://openalex.org/W2035003264","https://openalex.org/W2108286682","https://openalex.org/W2137092694","https://openalex.org/W2736601468","https://openalex.org/W2886854944","https://openalex.org/W2889711700","https://openalex.org/W2948652605","https://openalex.org/W2966735560","https://openalex.org/W2972143761","https://openalex.org/W2992833799","https://openalex.org/W3008245684","https://openalex.org/W3010946901","https://openalex.org/W3013679533","https://openalex.org/W3035700320","https://openalex.org/W3036186095","https://openalex.org/W3038822267","https://openalex.org/W3045014914","https://openalex.org/W3045509383","https://openalex.org/W3048735518","https://openalex.org/W3099352109","https://openalex.org/W3124981469","https://openalex.org/W3138294267","https://openalex.org/W3156919398","https://openalex.org/W3162945727","https://openalex.org/W3167122789","https://openalex.org/W3196924932","https://openalex.org/W3197308516","https://openalex.org/W4200325667","https://openalex.org/W4214717370","https://openalex.org/W4292086994","https://openalex.org/W4312838645","https://openalex.org/W4323519271","https://openalex.org/W4323519352","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6779282036"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W2355833770","https://openalex.org/W1985458517","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W3095877357","https://openalex.org/W2072565696","https://openalex.org/W2050451745","https://openalex.org/W2000675896"],"abstract_inverted_index":{"Extensive":[0],"research":[1],"has":[2],"been":[3],"dedicated":[4],"to":[5,29,65,72,76,97,136,144],"reinforcement":[6],"learning":[7],"(RL)":[8],"for":[9,48,112],"acquiring":[10],"proficient":[11],"optimal":[12,34,51,79,140],"controllers":[13,35],"through":[14],"interactions":[15],"with":[16],"the":[17,30,66,74,78,89,103,114,122,130,139,145,151],"environment.":[18],"However,":[19],"real-world":[20],"demands,":[21],"including":[22],"enhanced":[23],"safety":[24],"performance,":[25],"introduce":[26],"considerable":[27],"challenges":[28],"present":[31],"design":[32,101],"of":[33,121,150],"rooted":[36],"in":[37,45,81,92],"RL":[38],"algorithms.":[39],"A":[40,118],"novel":[41],"approach":[42],"is":[43,71,110,125],"introduced":[44],"this":[46],"article":[47],"designing":[49],"RL-based":[50,99],"controllers,":[52],"employing":[53],"a":[54,60,82],"control":[55,67,107],"barrier":[56],"function":[57,63],"(CBF)":[58],"alongside":[59],"nonquadratic":[61],"loss":[62],"related":[64],"signal.":[68],"The":[69],"aim":[70],"enable":[73],"agent":[75],"learn":[77,138],"controller":[80,100,115,141],"secure":[83],"and":[84,147],"efficient":[85],"manner.":[86],"To":[87],"tackle":[88],"instability":[90],"issue":[91],"neural":[93],"network":[94],"training":[95],"inherent":[96],"traditional":[98],"processes,":[102],"nonlinear":[104],"model":[105],"predictive":[106],"(NMPC)":[108],"technique":[109],"employed":[111],"initializing":[113],"network\u2019s":[116],"weights.":[117],"formal":[119],"demonstration":[120],"method\u2019s":[123],"optimality":[124],"presented.":[126],"Numerical":[127],"simulations":[128],"validate":[129],"proposed":[131],"approach,":[132],"illustrating":[133],"its":[134],"capacity":[135],"effectively":[137],"while":[142],"adhering":[143],"input":[146],"state":[148],"constraints":[149],"system.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}