{"id":"https://openalex.org/W2951650773","doi":"https://doi.org/10.1109/access.2019.2923845","title":"Data-Driven Integral Reinforcement Learning for Continuous-Time Non-Zero-Sum Games","display_name":"Data-Driven Integral Reinforcement Learning for Continuous-Time Non-Zero-Sum Games","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2951650773","doi":"https://doi.org/10.1109/access.2019.2923845","mag":"2951650773"},"language":"en","primary_location":{"id":"doi:10.1109/access.2019.2923845","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2923845","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08740904.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08740904.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053342436","display_name":"Yongliang Yang","orcid":"https://orcid.org/0000-0002-3144-8604"},"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":"Yongliang Yang","raw_affiliation_strings":["Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3144-8604","affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328729","display_name":"Liming Wang","orcid":"https://orcid.org/0000-0002-5732-5258"},"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":false,"raw_author_name":"Liming Wang","raw_affiliation_strings":["Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063118155","display_name":"Hamidreza Modares","orcid":"https://orcid.org/0000-0003-0800-5140"},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamidreza Modares","raw_affiliation_strings":["Department of Mechanical Engineering, Michigan State University, East Lansing, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073089333","display_name":"Da\u2010Wei Ding","orcid":"https://orcid.org/0000-0003-1201-7785"},"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":false,"raw_author_name":"Dawei Ding","raw_affiliation_strings":["Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101512101","display_name":"Yixin Yin","orcid":"https://orcid.org/0000-0001-6056-8878"},"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":false,"raw_author_name":"Yixin Yin","raw_affiliation_strings":["Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6056-8878","affiliations":[{"raw_affiliation_string":"Key Laboratory of Knowledge Automation for Industrial Processes, Ministry of Education, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038037619","display_name":"Donald C. Wunsch","orcid":"https://orcid.org/0000-0002-9726-9051"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Donald Wunsch","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053342436"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.8296,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.91522786,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"7","issue":null,"first_page":"82901","last_page":"82912"},"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":0.9865999817848206,"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":0.9147999882698059,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6644837856292725},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.626534640789032},{"id":"https://openalex.org/keywords/monotone-polygon","display_name":"Monotone polygon","score":0.6112720370292664},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.5633798241615295},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5316674709320068},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.523531436920166},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5213680863380432},{"id":"https://openalex.org/keywords/positive-definiteness","display_name":"Positive definiteness","score":0.4907428026199341},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.48079290986061096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4492071866989136},{"id":"https://openalex.org/keywords/integral-equation","display_name":"Integral equation","score":0.444580078125},{"id":"https://openalex.org/keywords/zero","display_name":"Zero (linguistics)","score":0.4388185441493988},{"id":"https://openalex.org/keywords/zero-sum-game","display_name":"Zero-sum game","score":0.42056751251220703},{"id":"https://openalex.org/keywords/positive-definite-matrix","display_name":"Positive-definite matrix","score":0.32597970962524414},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.12881061434745789}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6644837856292725},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.626534640789032},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.6112720370292664},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.5633798241615295},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5316674709320068},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.523531436920166},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5213680863380432},{"id":"https://openalex.org/C2778265155","wikidata":"https://www.wikidata.org/wiki/Q7233276","display_name":"Positive definiteness","level":4,"score":0.4907428026199341},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.48079290986061096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4492071866989136},{"id":"https://openalex.org/C27016315","wikidata":"https://www.wikidata.org/wiki/Q580101","display_name":"Integral equation","level":2,"score":0.444580078125},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.4388185441493988},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.42056751251220703},{"id":"https://openalex.org/C49712288","wikidata":"https://www.wikidata.org/wiki/Q77601250","display_name":"Positive-definite matrix","level":3,"score":0.32597970962524414},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.12881061434745789},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2019.2923845","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2923845","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08740904.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:feb3c63a32d04703825529907c53784f","is_oa":true,"landing_page_url":"https://doaj.org/article/feb3c63a32d04703825529907c53784f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 7, Pp 82901-82912 (2019)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2019.2923845","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2019.2923845","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8600701/08740904.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2985707575","display_name":null,"funder_award_id":"61873028","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G3094653860","display_name":null,"funder_award_id":"W911NF-18-2-0260","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G3895189458","display_name":null,"funder_award_id":"FRF-BD-17-002A","funder_id":"https://openalex.org/F4320325365","funder_display_name":"University of Science and Technology Beijing"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5523829882","display_name":null,"funder_award_id":"2018M641197","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G7934771358","display_name":null,"funder_award_id":"61333002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8505461575","display_name":null,"funder_award_id":"61873028","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/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320325365","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333675","display_name":"Intelligent Systems Center","ror":null},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951650773.pdf","grobid_xml":"https://content.openalex.org/works/W2951650773.grobid-xml"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W213289025","https://openalex.org/W602809265","https://openalex.org/W1513689897","https://openalex.org/W1581842928","https://openalex.org/W1614417283","https://openalex.org/W1804910891","https://openalex.org/W1972243698","https://openalex.org/W1988523476","https://openalex.org/W2019338681","https://openalex.org/W2020872085","https://openalex.org/W2048687352","https://openalex.org/W2068949505","https://openalex.org/W2089924634","https://openalex.org/W2100001575","https://openalex.org/W2100276679","https://openalex.org/W2102933137","https://openalex.org/W2104312287","https://openalex.org/W2148439597","https://openalex.org/W2156506338","https://openalex.org/W2189990206","https://openalex.org/W2287810892","https://openalex.org/W2475651303","https://openalex.org/W2484646121","https://openalex.org/W2529203006","https://openalex.org/W2564717627","https://openalex.org/W2579592432","https://openalex.org/W2580629550","https://openalex.org/W2581606339","https://openalex.org/W2585299106","https://openalex.org/W2600133099","https://openalex.org/W2772589676","https://openalex.org/W2789789879","https://openalex.org/W2793914020","https://openalex.org/W2798534591","https://openalex.org/W2802164917","https://openalex.org/W2803973384","https://openalex.org/W2896799653","https://openalex.org/W2918660012","https://openalex.org/W2919774326","https://openalex.org/W2963609304","https://openalex.org/W3150098721"],"related_works":["https://openalex.org/W2369793817","https://openalex.org/W2364489971","https://openalex.org/W2361979571","https://openalex.org/W3208377712","https://openalex.org/W2043819621","https://openalex.org/W2063005030","https://openalex.org/W2147922812","https://openalex.org/W4205226845","https://openalex.org/W2373372131","https://openalex.org/W1982955687"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"an":[3],"integral":[4,60,78],"value":[5],"iteration":[6,70],"(VI)":[7],"method":[8,62],"to":[9],"efficiently":[10],"find":[11],"online":[12,56],"the":[13,32,36,39,44,51,54,59,66,73,77,91,95,98,102,106,114,118,121],"Nash":[14,37],"equilibrium":[15],"solution":[16],"of":[17,53,76,83,90,97,120],"two-player":[18],"non-zero-sum":[19],"(NZS)":[20],"differential":[21],"games":[22],"for":[23,43],"linear":[24],"systems":[25],"with":[26,65],"partially":[27],"unknown":[28],"dynamics.":[29],"To":[30,49],"guarantee":[31,105],"closed-loop":[33,99],"stability":[34,96],"about":[35],"equilibrium,":[38],"explicit":[40],"upper":[41],"bound":[42],"discounted":[45],"factor":[46],"is":[47,63,109],"given.":[48],"show":[50],"efficacy":[52,119],"presented":[55,122],"model-free":[57],"solution,":[58],"VI":[61,79],"compared":[64],"model-based":[67],"off-line":[68],"policy":[69],"method.":[71],"Moreover,":[72],"theoretical":[74],"analysis":[75],"algorithm":[80],"in":[81,111],"terms":[82],"three":[84],"aspects,":[85],"i.e.,":[86],"positive":[87],"definiteness":[88],"properties":[89],"updated":[92],"cost":[93],"functions,":[94],"systems,":[100],"and":[101],"conditions":[103],"that":[104],"monotone":[107],"convergence,":[108],"provided":[110],"detail.":[112],"Finally,":[113],"simulation":[115],"results":[116],"demonstrate":[117],"algorithms.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2025-10-10T00:00:00"}