{"id":"https://openalex.org/W4416010742","doi":"https://doi.org/10.1109/tnnls.2025.3626762","title":"Inverse Reinforcement Learning for Disturbed Networked Nonlinear Systems With Data Dropouts","display_name":"Inverse Reinforcement Learning for Disturbed Networked Nonlinear Systems With Data Dropouts","publication_year":2025,"publication_date":"2025-11-07","ids":{"openalex":"https://openalex.org/W4416010742","doi":"https://doi.org/10.1109/tnnls.2025.3626762","pmid":"https://pubmed.ncbi.nlm.nih.gov/41201937"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3626762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3626762","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/A5026705701","display_name":"Pengfei Shi","orcid":"https://orcid.org/0009-0001-8169-8919"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengfei Shi","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and the International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0009-0001-8169-8919","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and the International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102973745","display_name":"Wenqian Xue","orcid":"https://orcid.org/0000-0002-3670-3854"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenqian Xue","raw_affiliation_strings":["Mechanical and Aerospace Engineering Department, University of Florida, Gainesville, FL, USA"],"raw_orcid":"https://orcid.org/0000-0002-3670-3854","affiliations":[{"raw_affiliation_string":"Mechanical and Aerospace Engineering Department, University of Florida, Gainesville, FL, USA","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033960992","display_name":"Jialu Fan","orcid":"https://orcid.org/0000-0001-7585-1166"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialu Fan","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and the International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"raw_orcid":"https://orcid.org/0000-0001-7585-1166","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and the International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["UTA Research Institute, The University of Texas at Arlington, Fort Worth, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-4074-1615","affiliations":[{"raw_affiliation_string":"UTA Research Institute, The University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001862814","display_name":"Bosen Lian","orcid":"https://orcid.org/0000-0002-3275-9551"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bosen Lian","raw_affiliation_strings":["Electrical and Computer Engineering Department, Auburn University, Auburn, AL, USA"],"raw_orcid":"https://orcid.org/0000-0002-3275-9551","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, Auburn University, Auburn, AL, USA","institution_ids":["https://openalex.org/I82497590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28590876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"37","issue":"4","first_page":"1978","last_page":"1990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.8906999826431274,"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":0.8906999826431274,"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":0.04149999842047691,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.008700000122189522,"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/trajectory","display_name":"Trajectory","score":0.7455999851226807},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6001999974250793},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5698999762535095},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4555000066757202},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.45260000228881836},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4287000000476837},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4065000116825104},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.40130001306533813}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7455999851226807},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492999792098999},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6001999974250793},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5698999762535095},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4065000116825104},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.40130001306533813},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.3635999858379364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3580999970436096},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C91581856","wikidata":"https://www.wikidata.org/wiki/Q2707001","display_name":"Nonlinear control","level":3,"score":0.3319999873638153},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3021000027656555},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C167123822","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automatic control","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3626762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3626762","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:41201937","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41201937","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/G3239473734","display_name":null,"funder_award_id":"XLYC2007135","funder_id":"https://openalex.org/F4320329895","funder_display_name":"Liaoning Revitalization Talents Program"},{"id":"https://openalex.org/G3474679019","display_name":null,"funder_award_id":"61991400","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/F4320329895","display_name":"Liaoning Revitalization Talents Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"article":[1],"develops":[2],"inverse":[3],"reinforcement":[4],"learning":[5],"(IRL)":[6],"control":[7,12,65,77,109],"algorithms":[8],"for":[9,80],"nonlinear":[10],"networked":[11],"systems":[13],"(NCSs)":[14],"to":[15,78,102],"mimic":[16],"trajectories":[17],"of":[18,32,45,54,64],"a":[19,85,95],"target":[20,46],"system":[21,118],"governed":[22],"by":[23,49,58,68],"an":[24],"unknown":[25],"optimal":[26,108],"cost":[27,105],"function,":[28],"despite":[29],"the":[30,50,59,69,104],"presence":[31],"random":[33],"data":[34,48,57,67,113,131],"dropouts":[35,40],"and":[36,61,82,107,133],"external":[37],"disturbances.":[38],"Data":[39],"occur":[41],"during:":[42],"1)":[43],"reception":[44,53,63],"trajectory":[47,125],"controller;":[51,60],"2)":[52],"state":[55],"feedback":[56],"3)":[62],"input":[66],"actuator.":[70],"By":[71],"organically":[72],"integrating":[73],"$H_{\\infty":[74],"}":[75],"$":[76],"account":[79],"disturbances":[81],"dropout-induced":[83],"uncertainty,":[84],"model-based":[86],"IRL":[87,98],"algorithm":[88,99],"is":[89,100],"first":[90],"developed.":[91],"Building":[92],"on":[93,117],"this,":[94],"neural-network-based":[96],"data-driven":[97],"developed":[101],"infer":[103],"function":[106],"policy":[110],"using":[111],"available":[112],"while":[114],"reducing":[115],"dependence":[116],"models.":[119],"The":[120],"proposed":[121],"methods":[122],"enable":[123],"effective":[124],"imitation":[126],"under":[127],"partial":[128],"model":[129],"knowledge,":[130],"dropouts,":[132],"disturbances,":[134],"as":[135],"demonstrated":[136],"through":[137],"simulation":[138],"studies.":[139]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-07T00:00:00"}