{"id":"https://openalex.org/W4412353450","doi":"https://doi.org/10.1109/tsmc.2025.3583212","title":"Online Reinforcement Learning Algorithm Design for Adaptive Optimal Consensus Control Under Interval Excitation","display_name":"Online Reinforcement Learning Algorithm Design for Adaptive Optimal Consensus Control Under Interval Excitation","publication_year":2025,"publication_date":"2025-07-11","ids":{"openalex":"https://openalex.org/W4412353450","doi":"https://doi.org/10.1109/tsmc.2025.3583212"},"language":"en","primary_location":{"id":"doi:10.1109/tsmc.2025.3583212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3583212","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/A5101933298","display_name":"Yong Xu","orcid":"https://orcid.org/0000-0003-0742-0510"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Xu","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0742-0510","affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qi-Yue Che","orcid":"https://orcid.org/0009-0009-5990-5844"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi-Yue Che","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-5990-5844","affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109412326","display_name":"Meng-Ying Wan","orcid":"https://orcid.org/0009-0009-1210-8733"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng-Ying Wan","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-1210-8733","affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040890553","display_name":"Di Mei","orcid":"https://orcid.org/0009-0000-0483-4959"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Di Mei","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-0483-4959","affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061204419","display_name":"Zheng\u2010Guang Wu","orcid":"https://orcid.org/0000-0003-4460-9785"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng-Guang Wu","raw_affiliation_strings":["Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4460-9785","affiliations":[{"raw_affiliation_string":"Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.17032364,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"55","issue":"10","first_page":"7325","last_page":"7334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14225","display_name":"Advanced Sensor and Control Systems","score":0.8199999928474426,"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"}},"topics":[{"id":"https://openalex.org/T14225","display_name":"Advanced Sensor and Control Systems","score":0.8199999928474426,"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/T13717","display_name":"Advanced Algorithms and Applications","score":0.7993999719619751,"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/T14474","display_name":"Industrial Technology and Control Systems","score":0.7095999717712402,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7722406387329102},{"id":"https://openalex.org/keywords/excitation","display_name":"Excitation","score":0.5153226256370544},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5104374289512634},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.4860542118549347},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.464966356754303},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.45769980549812317},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4202231466770172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36869221925735474},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.337574303150177},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23605123162269592},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17810091376304626},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.12063583731651306},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07069754600524902}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7722406387329102},{"id":"https://openalex.org/C83581075","wikidata":"https://www.wikidata.org/wiki/Q1361503","display_name":"Excitation","level":2,"score":0.5153226256370544},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5104374289512634},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.4860542118549347},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.464966356754303},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.45769980549812317},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4202231466770172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36869221925735474},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.337574303150177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23605123162269592},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17810091376304626},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.12063583731651306},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07069754600524902},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tsmc.2025.3583212","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tsmc.2025.3583212","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/G1357830632","display_name":null,"funder_award_id":"62322305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4513328056","display_name":null,"funder_award_id":"U1966202","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8783278860","display_name":null,"funder_award_id":"L241015","funder_id":"https://openalex.org/F4320334977","funder_display_name":"Beijing Municipal Natural Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334977","display_name":"Beijing Municipal Natural Science Foundation","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2037025184","https://openalex.org/W2108383324","https://openalex.org/W2430619152","https://openalex.org/W2570494446","https://openalex.org/W2580238099","https://openalex.org/W2580464663","https://openalex.org/W2765953808","https://openalex.org/W2790958326","https://openalex.org/W2899962524","https://openalex.org/W2921889099","https://openalex.org/W3138567228","https://openalex.org/W3146711799","https://openalex.org/W3196960188","https://openalex.org/W4200500895","https://openalex.org/W4206037914","https://openalex.org/W4280490104","https://openalex.org/W4281264198","https://openalex.org/W4285175516","https://openalex.org/W4285292987","https://openalex.org/W4292259193","https://openalex.org/W4301393358","https://openalex.org/W4311909242","https://openalex.org/W4312325945","https://openalex.org/W4317987765","https://openalex.org/W4322706796","https://openalex.org/W4367400016","https://openalex.org/W4381327650","https://openalex.org/W4386280756","https://openalex.org/W4386523235","https://openalex.org/W4386702821","https://openalex.org/W4388838248","https://openalex.org/W4390496261","https://openalex.org/W4393252810","https://openalex.org/W4403094316","https://openalex.org/W4406137535","https://openalex.org/W4409233386"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"This":[0],"article":[1],"proposes":[2],"online":[3,71,117],"data-based":[4,57],"reinforcement":[5],"learning":[6,73,76,86,180,200],"(RL)":[7],"algorithm":[8,74,181],"for":[9,41,48,75],"adaptive":[10,26,58],"output":[11],"consensus":[12],"control":[13,27,79,84,115],"of":[14,38,102,135,143,153,157,194,198,214],"heterogeneous":[15],"multiagent":[16],"systems":[17],"(MASs)":[18],"with":[19,64,187],"unknown":[20,188],"dynamics.":[21],"First,":[22],"we":[23,53],"employ":[24],"the":[25,39,46,49,77,90,95,99,113,141,144,151,159,195,210,215],"technique":[28],"to":[29,68,163,208],"design":[30],"a":[31,55,65,120,154,203],"distributed":[32],"observer,":[33],"which":[34],"provides":[35],"an":[36,70,128],"estimation":[37],"leader":[40],"partial":[42],"agents,":[43],"thereby":[44],"eliminating":[45],"need":[47],"global":[50],"information.":[51],"Then,":[52],"propose":[54],"novel":[56],"dynamic":[59],"programming":[60],"(ADP)":[61],"approach,":[62],"associated":[63],"double-integrator":[66],"operator,":[67],"develop":[69],"data-driven":[72,121],"optimal":[78,83,114,185],"policy.":[80],"However,":[81],"existing":[82,172,199],"strategy":[85],"algorithms":[87],"rely":[88],"on":[89,127,137],"persistent":[91],"excitation":[92,131],"conditions":[93,197],"(PECs),":[94],"full-rank":[96,160],"condition,":[97,133],"and":[98,165,212],"offline":[100],"storage":[101,168],"historical":[103,166],"data.":[104],"To":[105],"address":[106],"these":[107],"issues,":[108],"our":[109,178],"proposed":[110,179,216],"method":[111],"learns":[112],"policy":[116],"by":[118,149],"solving":[119],"linear":[122],"regression":[123],"equations":[124],"(LREs)":[125],"based":[126],"online-verifiable":[129],"interval":[130],"(IE)":[132],"instead":[134,156],"relying":[136],"PEC.":[138],"In":[139],"addition,":[140],"uniqueness":[142],"LRE":[145],"solution":[146],"is":[147,175,206],"established":[148],"verifying":[150],"invertibility":[152],"matrix,":[155],"satisfying":[158],"condition":[161],"related":[162],"PEC":[164],"data":[167],"as":[169],"required":[170],"in":[171],"algorithms.":[173,201,217],"It":[174],"demonstrated":[176],"that":[177],"not":[182],"only":[183],"guarantees":[184],"tracking":[186],"dynamics":[189],"but":[190],"also":[191],"relaxes":[192],"some":[193],"strict":[196],"Finally,":[202],"numerical":[204],"example":[205],"provided":[207],"validate":[209],"effectiveness":[211],"performance":[213]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}