{"id":"https://openalex.org/W2803973384","doi":"https://doi.org/10.1109/tcyb.2018.2830820","title":"Data-Based Reinforcement Learning for Nonzero-Sum Games With Unknown Drift Dynamics","display_name":"Data-Based Reinforcement Learning for Nonzero-Sum Games With Unknown Drift Dynamics","publication_year":2018,"publication_date":"2018-05-16","ids":{"openalex":"https://openalex.org/W2803973384","doi":"https://doi.org/10.1109/tcyb.2018.2830820","mag":"2803973384","pmid":"https://pubmed.ncbi.nlm.nih.gov/29994780"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2018.2830820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2018.2830820","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/A5049454999","display_name":"Qichao Zhang","orcid":"https://orcid.org/0000-0001-9747-391X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qichao Zhang","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9747-391X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8218-9633","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.8594,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.98306432,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"49","issue":"8","first_page":"2874","last_page":"2885"},"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":0.974399983882904,"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/T12047","display_name":"Viral Infections and Vectors","score":0.9646000266075134,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7415109872817993},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6689786911010742},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5594487190246582},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5512548089027405},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5418428182601929},{"id":"https://openalex.org/keywords/iterative-learning-control","display_name":"Iterative learning control","score":0.49344602227211},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4880908727645874},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.47557368874549866},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.46769285202026367},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.43485501408576965},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4229361116886139},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.40588653087615967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23886212706565857},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.20090287923812866},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1477898359298706}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7415109872817993},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6689786911010742},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5594487190246582},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5512548089027405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5418428182601929},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.49344602227211},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4880908727645874},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.47557368874549866},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.46769285202026367},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.43485501408576965},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4229361116886139},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40588653087615967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23886212706565857},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.20090287923812866},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1477898359298706},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2018.2830820","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2018.2830820","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:29994780","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29994780","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/G5745859652","display_name":null,"funder_award_id":"61573353","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7163010157","display_name":"\u57fa\u4e8e\u6570\u636e\u7684\u5efa\u7b51\u7fa4\u53ca\u5206\u5e03\u5f0f\u80fd\u6e90\u7cfb\u7edf\u4e00\u4f53\u5316\u5efa\u6a21\u4e0e\u81ea\u5b66\u4e60\u4f18\u5316\u63a7\u5236","funder_award_id":"61533017","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1559261542","https://openalex.org/W1588792722","https://openalex.org/W1606998818","https://openalex.org/W1614417283","https://openalex.org/W1793264465","https://openalex.org/W1912694276","https://openalex.org/W1972809999","https://openalex.org/W1979790866","https://openalex.org/W1991119064","https://openalex.org/W1997603681","https://openalex.org/W2012451615","https://openalex.org/W2019338681","https://openalex.org/W2019478222","https://openalex.org/W2032631296","https://openalex.org/W2039617089","https://openalex.org/W2052305027","https://openalex.org/W2055300044","https://openalex.org/W2068949505","https://openalex.org/W2073499686","https://openalex.org/W2081514674","https://openalex.org/W2088246243","https://openalex.org/W2102933137","https://openalex.org/W2108286682","https://openalex.org/W2120249358","https://openalex.org/W2121863487","https://openalex.org/W2139416664","https://openalex.org/W2145143778","https://openalex.org/W2164825665","https://openalex.org/W2183137222","https://openalex.org/W2208133488","https://openalex.org/W2249513906","https://openalex.org/W2312229020","https://openalex.org/W2330024298","https://openalex.org/W2405379562","https://openalex.org/W2462102501","https://openalex.org/W2475651303","https://openalex.org/W2480536132","https://openalex.org/W2489401300","https://openalex.org/W2554984891","https://openalex.org/W2568214755","https://openalex.org/W2583050531","https://openalex.org/W2585299106","https://openalex.org/W2586495351","https://openalex.org/W2589677408","https://openalex.org/W2605603065","https://openalex.org/W2606548817","https://openalex.org/W2946202185","https://openalex.org/W3125803449","https://openalex.org/W3150098721","https://openalex.org/W4214717370","https://openalex.org/W4234761190","https://openalex.org/W4285719527","https://openalex.org/W4302033101","https://openalex.org/W6729507393"],"related_works":["https://openalex.org/W3112009994","https://openalex.org/W2377964692","https://openalex.org/W2031608909","https://openalex.org/W2735003143","https://openalex.org/W2161232882","https://openalex.org/W3173893808","https://openalex.org/W2100719665","https://openalex.org/W2276545079","https://openalex.org/W1547192699","https://openalex.org/W2067285722"],"abstract_inverted_index":{"This":[0],"paper":[1],"is":[2,24,43,72,108],"concerned":[3],"about":[4],"the":[5,28,39,46,53,56,60,69,76,80,86,94,104,111,118,125,133,139,143,147,150],"nonlinear":[6,155],"optimization":[7],"problem":[8],"of":[9,31,55,79,89,121,132,149],"nonzero-sum":[10],"(NZS)":[11],"games":[12,33,71,157],"with":[13,158],"unknown":[14,159],"drift":[15,160],"dynamics.":[16,161],"The":[17,128],"data-based":[18,40,81,151],"integral":[19],"reinforcement":[20],"learning":[21,99,126],"(IRL)":[22],"method":[23,42],"proposed":[25,57],"to":[26,45],"approximate":[27],"Nash":[29],"equilibrium":[30],"NZS":[32,70,156],"iteratively.":[34],"Furthermore,":[35],"we":[36,84],"prove":[37],"that":[38,103],"IRL":[41,82,152],"equivalent":[44],"model-based":[47],"policy":[48],"iteration":[49],"algorithm,":[50],"which":[51,115],"guarantees":[52],"convergence":[54,119],"method.":[58,141],"For":[59],"implementation":[61],"purpose,":[62],"a":[63],"single-critic":[64],"neural":[65],"network":[66],"structure":[67],"for":[68,154],"given.":[73],"To":[74],"enhance":[75],"application":[77],"capability":[78],"method,":[83],"design":[85],"updating":[87],"laws":[88],"critic":[90,122,134],"weights":[91,123,135],"based":[92],"on":[93],"offline":[95],"and":[96],"online":[97,112],"iterative":[98,113],"methods,":[100],"respectively.":[101],"Note":[102],"experience":[105],"replay":[106],"technique":[107],"introduced":[109],"in":[110],"learning,":[114],"can":[116],"improve":[117],"rate":[120],"during":[124],"process.":[127],"uniform":[129],"ultimate":[130],"boundedness":[131],"are":[136],"guaranteed":[137],"using":[138],"Lyapunov":[140],"Finally,":[142],"numerical":[144],"results":[145],"demonstrate":[146],"effectiveness":[148],"algorithm":[153]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":19},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}