{"id":"https://openalex.org/W7134840437","doi":"https://doi.org/10.1109/jiot.2026.3672204","title":"Inverse Reinforcement Learning for Disturbance Rejection in Multiagent Systems","display_name":"Inverse Reinforcement Learning for Disturbance Rejection in Multiagent Systems","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134840437","doi":"https://doi.org/10.1109/jiot.2026.3672204"},"language":null,"primary_location":{"id":"doi:10.1109/jiot.2026.3672204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2026.3672204","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","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/A5020669784","display_name":"Huaipin Zhang","orcid":"https://orcid.org/0000-0001-6405-1382"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaipin Zhang","raw_affiliation_strings":["Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-6405-1382","affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069593829","display_name":"Weijie You","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijie You","raw_affiliation_strings":["Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128670511","display_name":"Wei Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I137056471","display_name":"Nanjing University of Finance and Economics","ror":"https://ror.org/031y8am81","country_code":"CN","type":"education","lineage":["https://openalex.org/I137056471"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhao","raw_affiliation_strings":["School of Computer and Artificial Intelligence, Nanjing University of Finance and Economics, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8045-2549","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence, Nanjing University of Finance and Economics, Nanjing, China","institution_ids":["https://openalex.org/I137056471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5128686861","display_name":"Dong Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Yue","raw_affiliation_strings":["Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7810-9338","affiliations":[{"raw_affiliation_string":"Institute of Advanced Technology for Carbon Neutrality, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]}]}],"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":0.30203876,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":"11","first_page":"24057","last_page":"24069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.7430999875068665,"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":0.7430999875068665,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.06040000170469284,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.03449999913573265,"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/convergence","display_name":"Convergence (economics)","score":0.6601999998092651},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.48980000615119934},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.48339998722076416},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4668000042438507},{"id":"https://openalex.org/keywords/mathematical-proof","display_name":"Mathematical proof","score":0.45320001244544983},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.42170000076293945},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4212999939918518},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.41909998655319214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7049999833106995},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6601999998092651},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.48980000615119934},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.48339998722076416},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4668000042438507},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.45320001244544983},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4212999939918518},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.41749998927116394},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3921999931335449},{"id":"https://openalex.org/C2777601987","wikidata":"https://www.wikidata.org/wiki/Q5283581","display_name":"Disturbance (geology)","level":2,"score":0.3765000104904175},{"id":"https://openalex.org/C195975749","wikidata":"https://www.wikidata.org/wiki/Q1475705","display_name":"Fuzzy control system","level":3,"score":0.37290000915527344},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3571999967098236},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34529998898506165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3140999972820282},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3125999867916107},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C58716799","wikidata":"https://www.wikidata.org/wiki/Q6035648","display_name":"Inner loop","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jiot.2026.3672204","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jiot.2026.3672204","pdf_url":null,"source":{"id":"https://openalex.org/S2480266640","display_name":"IEEE Internet of Things Journal","issn_l":"2327-4662","issn":["2327-4662","2372-2541"],"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 Internet of Things Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7937144976","display_name":null,"funder_award_id":"62573238","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8201404241","display_name":null,"funder_award_id":"BK20241889","funder_id":"https://openalex.org/F4320334982","funder_display_name":"Basic Research Program of Jiangsu Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334982","display_name":"Basic Research Program of Jiangsu Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"inverse":[3,74],"reinforcement":[4],"learning":[5],"(IRL)":[6],"algorithms":[7,130],"to":[8,19,28,107],"solve":[9],"the":[10,30,40,44,86,94,109,115,125,128],"optimal":[11,67,75],"synchronization":[12],"problems":[13],"for":[14],"multi-agent":[15],"systems":[16],"(MASs)":[17],"subject":[18],"disturbances.":[20],"A":[21],"framework":[22],"of":[23,34,47,97,120,127],"expert-learner":[24],"MASs":[25],"is":[26,82,131],"developed":[27],"reconstruct":[29],"unknown":[31],"cost":[32],"functions":[33],"expert":[35,48],"MAS.":[36],"Within":[37],"this":[38],"framework,":[39],"learner":[41],"MAS":[42,49],"imitates":[43],"behavior":[45],"trajectories":[46],"under":[50],"observation.":[51],"We":[52],"first":[53],"present":[54],"a":[55,78,134],"model-based":[56],"IRL":[57,80],"algorithm":[58,81],"including":[59],"two":[60,98],"iteration":[61],"loops:":[62],"an":[63,70],"inner":[64],"loop":[65,72],"on":[66,73],"control":[68],"and":[69,89,112,117],"outer":[71],"control.":[76],"Moreover,":[77],"modelfree":[79],"further":[83],"proposed":[84,122,129],"using":[85],"observed":[87],"input":[88],"state":[90],"data":[91],"without":[92],"requiring":[93],"dynamics":[95],"knowledge":[96],"MASs.":[99],"Then":[100],"generalized":[101],"fuzzy":[102],"hyperbolic":[103],"models":[104],"are":[105],"utilized":[106],"implement":[108],"model-free":[110],"algorithm,":[111],"we":[113],"provide":[114],"convergence":[116],"stabilization":[118],"proofs":[119],"our":[121],"algorithms.":[123],"Finally,":[124],"effectiveness":[126],"verified":[132],"through":[133],"simulation":[135],"example.":[136]},"counts_by_year":[],"updated_date":"2026-05-23T06:10:36.450269","created_date":"2026-03-11T00:00:00"}