{"id":"https://openalex.org/W2998579696","doi":"https://doi.org/10.1109/tcyb.2019.2957406","title":"Discrete-Time Non-Zero-Sum Games With Completely Unknown Dynamics","display_name":"Discrete-Time Non-Zero-Sum Games With Completely Unknown Dynamics","publication_year":2019,"publication_date":"2019-12-31","ids":{"openalex":"https://openalex.org/W2998579696","doi":"https://doi.org/10.1109/tcyb.2019.2957406","mag":"2998579696","pmid":"https://pubmed.ncbi.nlm.nih.gov/31902792"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2019.2957406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2019.2957406","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/A5040323322","display_name":"Ruizhuo Song","orcid":"https://orcid.org/0000-0002-6693-2738"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruizhuo Song","raw_affiliation_strings":["School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087825639","display_name":"Qinglai Wei","orcid":"https://orcid.org/0000-0001-7002-9800"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinglai Wei","raw_affiliation_strings":["State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100625790","display_name":"Huaguang Zhang","orcid":"https://orcid.org/0000-0002-0647-4050"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaguang Zhang","raw_affiliation_strings":["College of Information Science and Engineering, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Fort Worth, TX, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040323322"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":7.1973,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.97514312,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"51","issue":"6","first_page":"2929","last_page":"2943"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9832000136375427,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.9797000288963318,"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/algebraic-riccati-equation","display_name":"Algebraic Riccati equation","score":0.6585285663604736},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6274658441543579},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.602900505065918},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.5292443633079529},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.521725058555603},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.4826429486274719},{"id":"https://openalex.org/keywords/algebraic-equation","display_name":"Algebraic equation","score":0.466420978307724},{"id":"https://openalex.org/keywords/kronecker-product","display_name":"Kronecker product","score":0.46416404843330383},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45940178632736206},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4570496380329132},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.45275047421455383},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.43631523847579956},{"id":"https://openalex.org/keywords/system-dynamics","display_name":"System dynamics","score":0.4183392822742462},{"id":"https://openalex.org/keywords/riccati-equation","display_name":"Riccati equation","score":0.3770318329334259},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3664965331554413},{"id":"https://openalex.org/keywords/kronecker-delta","display_name":"Kronecker delta","score":0.3658314347267151},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.26610928773880005},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.20633593201637268},{"id":"https://openalex.org/keywords/differential-equation","display_name":"Differential equation","score":0.11863413453102112},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.09355512261390686}],"concepts":[{"id":"https://openalex.org/C13847129","wikidata":"https://www.wikidata.org/wiki/Q4723989","display_name":"Algebraic Riccati equation","level":4,"score":0.6585285663604736},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6274658441543579},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.602900505065918},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5292443633079529},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.521725058555603},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.4826429486274719},{"id":"https://openalex.org/C23917780","wikidata":"https://www.wikidata.org/wiki/Q50698","display_name":"Algebraic equation","level":3,"score":0.466420978307724},{"id":"https://openalex.org/C46030957","wikidata":"https://www.wikidata.org/wiki/Q1238125","display_name":"Kronecker product","level":3,"score":0.46416404843330383},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45940178632736206},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4570496380329132},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.45275047421455383},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.43631523847579956},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.4183392822742462},{"id":"https://openalex.org/C45473103","wikidata":"https://www.wikidata.org/wiki/Q851503","display_name":"Riccati equation","level":3,"score":0.3770318329334259},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3664965331554413},{"id":"https://openalex.org/C39482219","wikidata":"https://www.wikidata.org/wiki/Q192826","display_name":"Kronecker delta","level":2,"score":0.3658314347267151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.26610928773880005},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.20633593201637268},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.11863413453102112},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.09355512261390686},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2019.2957406","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2019.2957406","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:31902792","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31902792","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":[{"score":0.4699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2375880139","display_name":null,"funder_award_id":"FRF-BD-19-002A","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6603537307","display_name":null,"funder_award_id":"61722312","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6647187102","display_name":null,"funder_award_id":"61873300","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation 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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1519369336","https://openalex.org/W1680219837","https://openalex.org/W1912694276","https://openalex.org/W1968908471","https://openalex.org/W1969959431","https://openalex.org/W1986864433","https://openalex.org/W1991119064","https://openalex.org/W2011310556","https://openalex.org/W2011866373","https://openalex.org/W2019338681","https://openalex.org/W2035608030","https://openalex.org/W2039354440","https://openalex.org/W2068949505","https://openalex.org/W2073591687","https://openalex.org/W2086977346","https://openalex.org/W2093831009","https://openalex.org/W2122671188","https://openalex.org/W2137531403","https://openalex.org/W2148439597","https://openalex.org/W2152161277","https://openalex.org/W2183137222","https://openalex.org/W2214884926","https://openalex.org/W2249513906","https://openalex.org/W2339745223","https://openalex.org/W2343701426","https://openalex.org/W2345052385","https://openalex.org/W2475651303","https://openalex.org/W2484646121","https://openalex.org/W2529203006","https://openalex.org/W2548277951","https://openalex.org/W2570494446","https://openalex.org/W2580629550","https://openalex.org/W2727450595","https://openalex.org/W2756081914","https://openalex.org/W2802027610","https://openalex.org/W2896789078","https://openalex.org/W2912270658","https://openalex.org/W2963609304","https://openalex.org/W3103456419","https://openalex.org/W3148386102"],"related_works":["https://openalex.org/W123417539","https://openalex.org/W2005019312","https://openalex.org/W2105459831","https://openalex.org/W1546579375","https://openalex.org/W1563296412","https://openalex.org/W2127238600","https://openalex.org/W2114791549","https://openalex.org/W16457797","https://openalex.org/W2792258377","https://openalex.org/W1530596433"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"off-policy":[3,62,74],"reinforcement":[4],"learning":[5],"(RL)":[6],"algorithm":[7,38],"is":[8,39,57,65,80,97,124,143,157],"established":[9],"to":[10,41,88,126],"solve":[11],"the":[12,43,54,89,92,104,111,128,148,160],"discrete-time":[13,68,152],"N":[14,24,44,69,75,93,112,133],"-player":[15,70],"nonzero-sum":[16],"(NZS)":[17],"games":[18,156],"with":[19],"completely":[20],"unknown":[21,100,153],"dynamics.":[22,120],"The":[23,73,121,138,145],"-coupled":[25,76,94,113],"generalized":[26],"algebraic":[27],"Riccati":[28],"equations":[29],"(GARE)":[30],"are":[31],"derived,":[32],"and":[33,49,103,132],"then":[34],"policy":[35],"iteration":[36],"(PI)":[37],"used":[40,125],"obtain":[42],"-tuple":[45,134],"of":[46,118,135,140,147],"iterative":[47,50,129,136],"control":[48],"value":[51,85,130],"function.":[52],"As":[53],"system":[55,105,119],"dynamics":[56,154],"necessary":[58],"in":[59],"PI":[60],"algorithm,":[61],"RL":[63],"method":[64,150],"developed":[66],"for":[67,151],"NZS":[71,155],"games.":[72],"Hamilton-Jacobi":[77],"(HJ)":[78],"equation":[79,96,115],"derived":[81],"based":[82],"on":[83],"quadratic":[84],"functions.":[86],"According":[87],"Kronecker":[90],"product,":[91],"HJ":[95,114],"decomposed":[98],"into":[99],"parameter":[101],"part":[102],"operation":[106],"data":[107],"part,":[108],"which":[109],"makes":[110],"solved":[116],"independent":[117],"least":[122],"square":[123],"calculate":[127],"function":[131],"control.":[137],"existence":[139],"Nash":[141],"equilibrium":[142],"proved.":[144],"result":[146],"proposed":[149],"indicated":[158],"by":[159],"simulation":[161],"examples.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
