{"id":"https://openalex.org/W4412985095","doi":"https://doi.org/10.1109/tcyb.2025.3587682","title":"Memory-Efficient Inverse Reinforcement Learning for Multiplayer Differential Games","display_name":"Memory-Efficient Inverse Reinforcement Learning for Multiplayer Differential Games","publication_year":2025,"publication_date":"2025-08-05","ids":{"openalex":"https://openalex.org/W4412985095","doi":"https://doi.org/10.1109/tcyb.2025.3587682","pmid":"https://pubmed.ncbi.nlm.nih.gov/40763048"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2025.3587682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2025.3587682","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","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/A5011843182","display_name":"Jiacheng Wu","orcid":"https://orcid.org/0000-0001-7607-8777"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacheng Wu","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology and the Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-7607-8777","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology and the Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838","https://openalex.org/I55712492"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101996724","display_name":"Yang Zhu","orcid":"https://orcid.org/0000-0003-4110-6445"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhu","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology and the Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4110-6445","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology and the Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838","https://openalex.org/I55712492"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078403818","display_name":"Hongye Su","orcid":"https://orcid.org/0000-0002-7003-1000"},"institutions":[{"id":"https://openalex.org/I4391767838","display_name":"State Key Laboratory of Industrial Control Technology","ror":"https://ror.org/03a33a786","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391767838","https://openalex.org/I76130692"]},{"id":"https://openalex.org/I55712492","display_name":"Zhejiang University of Technology","ror":"https://ror.org/02djqfd08","country_code":"CN","type":"education","lineage":["https://openalex.org/I55712492"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongye Su","raw_affiliation_strings":["State Key Laboratory of Industrial Control Technology and the Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7003-1000","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Industrial Control Technology and the Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I4391767838","https://openalex.org/I55712492"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2699,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84999137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"55","issue":"11","first_page":"5545","last_page":"5558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9624000191688538,"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":0.9624000191688538,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6644760966300964},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5954169631004333},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5837656259536743},{"id":"https://openalex.org/keywords/differential","display_name":"Differential (mechanical device)","score":0.5817182660102844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3459925651550293},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.31479454040527344},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.13491931557655334},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09565317630767822}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6644760966300964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5954169631004333},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5837656259536743},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.5817182660102844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3459925651550293},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31479454040527344},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13491931557655334},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09565317630767822},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2025.3587682","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2025.3587682","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"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 Cybernetics","raw_type":"journal-article"},{"id":"pmid:40763048","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40763048","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 cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2335503236","display_name":null,"funder_award_id":"62303410","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2943320288","display_name":null,"funder_award_id":"ICT2025B78","funder_id":"https://openalex.org/F4320326952","funder_display_name":"State Key Laboratory of Industrial Control Technology"},{"id":"https://openalex.org/G5064689612","display_name":null,"funder_award_id":"2025C01022","funder_id":"https://openalex.org/F4320329801","funder_display_name":"Shenzhen Research and Development Program"},{"id":"https://openalex.org/G5704152552","display_name":null,"funder_award_id":"ICT2025B09","funder_id":"https://openalex.org/F4320326952","funder_display_name":"State Key Laboratory of Industrial Control Technology"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320326952","display_name":"State Key Laboratory of Industrial Control Technology","ror":null},{"id":"https://openalex.org/F4320329801","display_name":"Shenzhen Research and Development Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1999874108","https://openalex.org/W2019338681","https://openalex.org/W2046972933","https://openalex.org/W2125256511","https://openalex.org/W2475651303","https://openalex.org/W2492629073","https://openalex.org/W2579592432","https://openalex.org/W2734548765","https://openalex.org/W2942027162","https://openalex.org/W2983464671","https://openalex.org/W2990694606","https://openalex.org/W2996568167","https://openalex.org/W2998579696","https://openalex.org/W3013559981","https://openalex.org/W3037298378","https://openalex.org/W3114263192","https://openalex.org/W3156476459","https://openalex.org/W3191504080","https://openalex.org/W3195322794","https://openalex.org/W3197005866","https://openalex.org/W3203504876","https://openalex.org/W4205159341","https://openalex.org/W4210732025","https://openalex.org/W4283835015","https://openalex.org/W4290991295","https://openalex.org/W4311909242","https://openalex.org/W4313130271","https://openalex.org/W4327522695","https://openalex.org/W4328007490","https://openalex.org/W4377971518","https://openalex.org/W4378805020","https://openalex.org/W4381162568","https://openalex.org/W4388076083","https://openalex.org/W4391554350","https://openalex.org/W4392476537","https://openalex.org/W4395056607","https://openalex.org/W4396909851","https://openalex.org/W4399665804","https://openalex.org/W4399666171","https://openalex.org/W4400078339","https://openalex.org/W4400723679","https://openalex.org/W4400877505","https://openalex.org/W4403182809","https://openalex.org/W4403826514"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Data-driven":[0],"inverse":[1,57,95],"reinforcement":[2],"learning":[3],"(RL)":[4],"control":[5,97,105],"aims":[6],"to":[7,30,111],"infer":[8],"the":[9,66,81,149,158,161],"unknown":[10],"cost":[11],"function":[12],"of":[13,22,148,160],"a":[14,26,54,88,122,140],"learner":[15,82,133],"system":[16,83],"from":[17],"expert":[18],"demonstrations.":[19],"The":[20],"convergence":[21],"existing":[23,94],"methods":[24],"necessitates":[25],"data":[27,72],"storage":[28],"mechanism":[29],"maintain":[31],"persistent":[32],"excitation":[33,91],"(PE),":[34],"which":[35,108,128],"consumes":[36],"memory":[37],"and":[38,71,155,169],"induces":[39],"delays":[40],"in":[41,49,113],"satisfying":[42],"full-rank":[43],"conditions.":[44],"To":[45],"address":[46,117],"these":[47],"problems,":[48],"this":[50,118],"article,":[51],"we":[52,144],"propose":[53],"novel":[55,123],"memory-efficient":[56],"RL":[58,96,126],"algorithm":[59],"for":[60,68,80,132],"multiplayer":[61],"differential":[62],"game":[63],"that":[64,76],"eliminates":[65],"need":[67],"strict":[69],"PE":[70],"storage.":[73],"We":[74,116],"prove":[75],"Nash":[77],"equilibrium":[78],"solutions":[79],"can":[84],"be":[85],"guaranteed":[86],"under":[87],"mild":[89],"initial":[90,103],"condition.":[92],"Besides,":[93],"algorithms":[98,163],"often":[99],"rely":[100],"on":[101],"an":[102,130],"admissible":[104],"policy":[106],"(IACP),":[107],"is":[109,164],"difficult":[110],"obtain":[112],"data-driven":[114],"scenarios.":[115],"problem":[119],"by":[120,135,166],"designing":[121],"filter-based":[124],"homotopic":[125],"algorithm,":[127],"derives":[129],"IACP":[131],"systems":[134],"shifting":[136],"unstable":[137],"poles":[138],"into":[139],"stable":[141],"region.":[142],"Moreover,":[143],"establish":[145],"several":[146],"properties":[147],"designed":[150],"algorithms,":[151],"including":[152],"convergence,":[153],"nonuniqueness,":[154],"stability.":[156],"Finally,":[157],"effectiveness":[159],"proposed":[162],"verified":[165],"comparative":[167],"studies":[168],"simulation":[170],"results.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}