{"id":"https://openalex.org/W4413464951","doi":"https://doi.org/10.1109/tcsi.2025.3598198","title":"Distributed Data-Driven Inverse Reinforcement Learning for Multi-Agent Systems","display_name":"Distributed Data-Driven Inverse Reinforcement Learning for Multi-Agent Systems","publication_year":2025,"publication_date":"2025-08-14","ids":{"openalex":"https://openalex.org/W4413464951","doi":"https://doi.org/10.1109/tcsi.2025.3598198"},"language":"en","primary_location":{"id":"doi:10.1109/tcsi.2025.3598198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2025.3598198","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 Circuits and Systems I: Regular Papers","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/A5101913741","display_name":"Yingying Yang","orcid":"https://orcid.org/0000-0002-1247-1112"},"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":"Yingying Yang","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/A5100434523","display_name":"Wei Zhao","orcid":"https://orcid.org/0000-0001-8045-2549"},"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/A5100727487","display_name":"Dong Yue","orcid":"https://orcid.org/0000-0001-7810-9338"},"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":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85543156,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"73","issue":"4","first_page":"2892","last_page":"2899"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9258000254631042,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9258000254631042,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9197999835014343,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5974388122558594},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5896450281143188},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.5395748615264893},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4976804554462433},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4177109897136688},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3563659191131592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2890705466270447},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20612472295761108},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1843230128288269},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.10451894998550415},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.09337237477302551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5974388122558594},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5896450281143188},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.5395748615264893},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4976804554462433},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4177109897136688},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3563659191131592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2890705466270447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20612472295761108},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1843230128288269},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.10451894998550415},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.09337237477302551},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsi.2025.3598198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2025.3598198","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"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 Circuits and Systems I: Regular Papers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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],"paper":[1],"presents":[2],"a":[3,77,107],"distributed":[4,78],"data-driven":[5,79],"inverse":[6],"reinforcement":[7],"learning":[8],"(IRL)":[9],"framework":[10],"for":[11,64],"multiagent":[12],"systems":[13],"using":[14],"state":[15,21],"trajectories":[16],"only.":[17],"By":[18],"exploiting":[19],"the":[20,23,62,65,84,89,99],"observations,":[22],"approach":[24,81,101],"achieves":[25],"optimal":[26],"consensus":[27,96],"among":[28],"agents":[29],"while":[30],"simultaneously":[31],"inferring":[32],"unknown":[33,54],"cost":[34],"functions":[35],"of":[36,67,87],"all":[37],"agents.":[38],"Concurrent":[39],"learning-based":[40],"adaptive":[41],"laws":[42],"and":[43,53,82,93],"parameter":[44],"estimators":[45],"are":[46],"designed":[47],"to":[48],"estimate":[49,91],"feedback":[50],"control":[51],"gains":[52],"system\u2019s":[55],"dynamics":[56],"in":[57],"real":[58],"time,":[59],"which":[60],"mitigates":[61],"requirement":[63],"persistency":[66],"excitation":[68],"condition.":[69],"Building":[70],"on":[71,106],"these":[72],"learned":[73],"models,":[74],"we":[75],"develop":[76],"IRL":[80],"analyze":[83],"ultimate":[85],"boundedness":[86],"both":[88],"weight":[90],"errors":[92],"local":[94],"neighbor":[95],"errors.":[97],"Finally,":[98],"proposed":[100],"is":[102],"validated":[103],"through":[104],"simulations":[105],"DC":[108],"islanded":[109],"microgrid.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-31T06:02:25.137627","created_date":"2025-10-10T00:00:00"}