{"id":"https://openalex.org/W4312714074","doi":"https://doi.org/10.1109/tcsi.2022.3221274","title":"Off-Policy Model-Free Learning for Multi-Player Non-Zero-Sum Games With Constrained Inputs","display_name":"Off-Policy Model-Free Learning for Multi-Player Non-Zero-Sum Games With Constrained Inputs","publication_year":2022,"publication_date":"2022-11-15","ids":{"openalex":"https://openalex.org/W4312714074","doi":"https://doi.org/10.1109/tcsi.2022.3221274"},"language":"en","primary_location":{"id":"doi:10.1109/tcsi.2022.3221274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2022.3221274","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/A5100701044","display_name":"Yu Huo","orcid":"https://orcid.org/0000-0002-8807-106X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Huo","raw_affiliation_strings":["Beijing Key Laboratory of Computational Intelligence and Intelligent System and the Beijing Laboratory of Smart Environmental Protection, Faculty of Information Technology, Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8807-106X","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Computational Intelligence and Intelligent System and the Beijing Laboratory of Smart Environmental Protection, Faculty of Information Technology, Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024549341","display_name":"Ding Wang","orcid":"https://orcid.org/0000-0002-7149-5712"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Wang","raw_affiliation_strings":["Beijing Key Laboratory of Computational Intelligence and Intelligent System and the Beijing Laboratory of Smart Environmental Protection, Faculty of Information Technology, Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7149-5712","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Computational Intelligence and Intelligent System and the Beijing Laboratory of Smart Environmental Protection, Faculty of Information Technology, Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055432844","display_name":"Junfei Qiao","orcid":"https://orcid.org/0000-0002-1707-6074"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junfei Qiao","raw_affiliation_strings":["Beijing Key Laboratory of Computational Intelligence and Intelligent System and the Beijing Laboratory of Smart Environmental Protection, Faculty of Information Technology, Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1707-6074","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Computational Intelligence and Intelligent System and the Beijing Laboratory of Smart Environmental Protection, Faculty of Information Technology, Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101711547","display_name":"Menghua Li","orcid":"https://orcid.org/0000-0002-7231-7555"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Menghua Li","raw_affiliation_strings":["Beijing Key Laboratory of Computational Intelligence and Intelligent System and the Beijing Laboratory of Smart Environmental Protection, Faculty of Information Technology, Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7231-7555","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Computational Intelligence and Intelligent System and the Beijing Laboratory of Smart Environmental Protection, Faculty of Information Technology, Beijing Institute of Artificial Intelligence, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":4.1188,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.94983467,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"70","issue":"2","first_page":"910","last_page":"920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"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":0.9998999834060669,"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/T12047","display_name":"Viral Infections and Vectors","score":0.9857000112533569,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12485","display_name":"Optimism, Hope, and Well-being","score":0.9329000115394592,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7273429036140442},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6899846792221069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.653798520565033},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.6304118633270264},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5668717622756958},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5639127492904663},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.4835493266582489},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.48132097721099854},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4738110601902008},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.45485830307006836},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4465211033821106},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4315350651741028},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.28648632764816284},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2809225916862488},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23564526438713074},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22922098636627197}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7273429036140442},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6899846792221069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.653798520565033},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.6304118633270264},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5668717622756958},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5639127492904663},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.4835493266582489},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.48132097721099854},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4738110601902008},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.45485830307006836},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4465211033821106},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4315350651741028},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28648632764816284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2809225916862488},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23564526438713074},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22922098636627197},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsi.2022.3221274","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2022.3221274","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":[{"display_name":"Peace, Justice and strong institutions","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3173892580","display_name":null,"funder_award_id":"JQ19013","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G332087857","display_name":null,"funder_award_id":"2021ZD0112301","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G339866880","display_name":null,"funder_award_id":"61890930\u20135","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3929591211","display_name":null,"funder_award_id":"62021003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4553196225","display_name":null,"funder_award_id":"62222301","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8400715902","display_name":null,"funder_award_id":"2021ZD011 2302","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G99439497","display_name":null,"funder_award_id":"2018YFC1900800-5","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":57,"referenced_works":["https://openalex.org/W1793264465","https://openalex.org/W1991119064","https://openalex.org/W2012451615","https://openalex.org/W2024303516","https://openalex.org/W2068949505","https://openalex.org/W2074229485","https://openalex.org/W2081514674","https://openalex.org/W2085194340","https://openalex.org/W2088246243","https://openalex.org/W2108286682","https://openalex.org/W2108383324","https://openalex.org/W2183137222","https://openalex.org/W2475651303","https://openalex.org/W2489401300","https://openalex.org/W2579592432","https://openalex.org/W2590419786","https://openalex.org/W2605628695","https://openalex.org/W2755577605","https://openalex.org/W2792596411","https://openalex.org/W2803973384","https://openalex.org/W2896789078","https://openalex.org/W2897507137","https://openalex.org/W2908643158","https://openalex.org/W2908707124","https://openalex.org/W2914240983","https://openalex.org/W2921869787","https://openalex.org/W2981047237","https://openalex.org/W2983464671","https://openalex.org/W2986168313","https://openalex.org/W2998579696","https://openalex.org/W2998971133","https://openalex.org/W3009005446","https://openalex.org/W3012269643","https://openalex.org/W3037606975","https://openalex.org/W3045930817","https://openalex.org/W3048753297","https://openalex.org/W3093328126","https://openalex.org/W3096135216","https://openalex.org/W3097662863","https://openalex.org/W3114263192","https://openalex.org/W3124444594","https://openalex.org/W3129522656","https://openalex.org/W3130054631","https://openalex.org/W3131597141","https://openalex.org/W3137847746","https://openalex.org/W3162439934","https://openalex.org/W3172595528","https://openalex.org/W3189325691","https://openalex.org/W3200066794","https://openalex.org/W3201329083","https://openalex.org/W3209518740","https://openalex.org/W3213700990","https://openalex.org/W4200008856","https://openalex.org/W4205939747","https://openalex.org/W4224211769","https://openalex.org/W4241906476","https://openalex.org/W4283727098"],"related_works":["https://openalex.org/W2761624296","https://openalex.org/W4386994694","https://openalex.org/W4388738109","https://openalex.org/W2362901947","https://openalex.org/W2362086884","https://openalex.org/W1606071314","https://openalex.org/W2350210972","https://openalex.org/W2369126164","https://openalex.org/W1482785882","https://openalex.org/W2376218423"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"multi-player":[3],"non-zero-sum":[4],"games":[5],"with":[6],"control":[7,117],"constraints":[8],"are":[9,122,150],"studied":[10],"by":[11,58,95,124],"utilizing":[12,125],"a":[13,52],"novel":[14],"model-free":[15,53,83,101],"approach":[16,94,103],"based":[17,67],"on":[18,68,142],"adaptive":[19],"dynamic":[20],"programming":[21],"framework.":[22,159],"First,":[23],"the":[24,34,38,46,49,60,69,73,82,88,91,97,100,105,111,114,116,126,137,143,154,157],"model-based":[25,106],"policy":[26,118],"iteration":[27],"(PI)":[28],"method":[29,55],"is":[30,40,56,76,133],"provided,":[31],"which":[32],"requires":[33],"system":[35,50,74],"dynamics,":[36,51],"and":[37,104,119],"convergence":[39,89],"demonstrated.":[41],"Then,":[42],"aiming":[43],"to":[44,80,135,152],"eliminate":[45],"need":[47],"for":[48],"iterative":[54,102,107],"obtained":[57],"using":[59],"off-policy":[61,92],"integral":[62],"reinforcement":[63],"learning":[64],"(IRL)":[65],"scheme":[66],"PI":[70],"approach.":[71,84,108],"Moreover,":[72],"data":[75,145],"collected":[77,144],"in":[78,110],"order":[79],"construct":[81],"Besides,":[85],"we":[86],"analyze":[87],"of":[90,113,156],"IRL":[93],"proving":[96],"equivalence":[98],"between":[99],"Remarkably,":[109],"implementation":[112],"scheme,":[115],"cost":[120],"function":[121],"approximated":[123],"actor-critic":[127,138],"networks.":[128],"The":[129],"least":[130],"square":[131],"algorithm":[132],"utilized":[134],"learn":[136],"networks":[139],"weights":[140],"depended":[141],"sets.":[146],"Finally,":[147],"two":[148],"cases":[149],"provided":[151],"demonstrate":[153],"effectiveness":[155],"established":[158]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":5}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}