{"id":"https://openalex.org/W4416251581","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229184","title":"Online Continual Reinforcement Learning-Based Optimal Output Tracking Control of Nonlinear Systems Using a Multilayer Observer","display_name":"Online Continual Reinforcement Learning-Based Optimal Output Tracking Control of Nonlinear Systems Using a Multilayer Observer","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251581","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229184"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5029416048","display_name":"Irfan Ganie","orcid":"https://orcid.org/0000-0002-0376-735X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Irfan Ganie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5034957233","display_name":"Suresh Jagannathan","orcid":"https://orcid.org/0000-0001-6871-2424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Jagannathan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029416048"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34723428,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9976000189781189,"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":0.9976000189781189,"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":0.0005000000237487257,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":9.999999747378752e-05,"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":0.7839000225067139},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7454000115394592},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.6230999827384949},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6169000267982483},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5845000147819519},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.517300009727478},{"id":"https://openalex.org/keywords/output-feedback","display_name":"Output feedback","score":0.4083000123500824},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.3901999890804291},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.387800008058548}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7839000225067139},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7454000115394592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6309999823570251},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6169000267982483},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5845000147819519},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C3018623182","wikidata":"https://www.wikidata.org/wiki/Q154021","display_name":"Output feedback","level":3,"score":0.4083000123500824},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.38440001010894775},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C62431964","wikidata":"https://www.wikidata.org/wiki/Q2271572","display_name":"Separation principle","level":4,"score":0.3165999948978424},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C91581856","wikidata":"https://www.wikidata.org/wiki/Q2707001","display_name":"Nonlinear control","level":3,"score":0.30059999227523804},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.28940001130104065},{"id":"https://openalex.org/C3031470","wikidata":"https://www.wikidata.org/wiki/Q818544","display_name":"State observer","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C115527620","wikidata":"https://www.wikidata.org/wiki/Q769909","display_name":"Nonlinear programming","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2612999975681305},{"id":"https://openalex.org/C183356978","wikidata":"https://www.wikidata.org/wiki/Q1779213","display_name":"Tracking error","level":3,"score":0.26030001044273376},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229184","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229184","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1517236425","https://openalex.org/W1968908471","https://openalex.org/W2012451615","https://openalex.org/W2093098144","https://openalex.org/W2151966330","https://openalex.org/W2498331080","https://openalex.org/W2560647685","https://openalex.org/W2791869553","https://openalex.org/W2897702175","https://openalex.org/W3041482332","https://openalex.org/W3121634745","https://openalex.org/W3124444594","https://openalex.org/W4301392153","https://openalex.org/W4399563101"],"related_works":[],"abstract_inverted_index":{"A":[0],"scalable":[1],"output":[2,110,120],"feedback":[3,111,121],"control":[4,64,123],"framework":[5],"utilizing":[6],"a":[7,14,32,95,129,134],"multilayer":[8],"neural":[9],"network":[10,16,72],"(MNN)":[11],"observer":[12,38],"and":[13,23,39,58,74,83],"critic":[15,40,71,100],"via":[17],"an":[18,86],"integral":[19],"reinforcement":[20],"learning":[21,82,89],"(IRL)":[22],"adaptive":[24],"dynamic":[25],"programming":[26],"(ADP)":[27],"approach":[28],"is":[29,66,91,124],"proposed":[30,117],"for":[31],"class":[33],"of":[34,51,115],"nonlinear":[35],"systems.":[36],"The":[37,62,113],"MNN":[41,53,101],"weight":[42],"updates":[43],"are":[44],"derived":[45],"using":[46],"singular":[47],"value":[48],"decomposition":[49],"(SVD)":[50],"the":[52,70,75,99,109,116,143],"activation":[54],"gradients,":[55],"measured":[56],"outputs,":[57],"Bellman":[59],"errors,":[60],"respectively.":[61],"optimal":[63,119],"input":[65],"computed":[67],"based":[68],"on":[69,105,128],"weights":[73],"observer-estimated":[76],"system":[77],"dynamics.":[78],"To":[79],"enable":[80],"multitask":[81],"knowledge":[84],"retention,":[85],"online":[87],"continual":[88],"mechanism":[90],"incorporated":[92],"by":[93],"introducing":[94],"penalty":[96],"function":[97],"into":[98],"updates,":[102],"relying":[103],"solely":[104],"estimated":[106],"states":[107],"in":[108,142],"setting.":[112],"effectiveness":[114],"MNN-based":[118],"tracking":[122],"validated":[125],"through":[126],"simulations":[127],"two-link":[130],"robotic":[131],"manipulator,":[132],"achieving":[133],"75%":[135],"performance":[136],"improvement":[137],"compared":[138],"to":[139],"recent":[140],"methods":[141],"literature.":[144]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}