{"id":"https://openalex.org/W3134387361","doi":"https://doi.org/10.1109/tcyb.2021.3052832","title":"<i>Q</i>-Learning for Feedback Nash Strategy of Finite-Horizon Nonzero-Sum Difference Games","display_name":"<i>Q</i>-Learning for Feedback Nash Strategy of Finite-Horizon Nonzero-Sum Difference Games","publication_year":2021,"publication_date":"2021-03-12","ids":{"openalex":"https://openalex.org/W3134387361","doi":"https://doi.org/10.1109/tcyb.2021.3052832","mag":"3134387361","pmid":"https://pubmed.ncbi.nlm.nih.gov/33710965"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2021.3052832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2021.3052832","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/A5008453377","display_name":"Zhaorong Zhang","orcid":"https://orcid.org/0000-0002-6755-9795"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Zhaorong Zhang","raw_affiliation_strings":["School of Electrical Engineering and Computing, University of Newcastle, Callaghan, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computing, University of Newcastle, Callaghan, NSW, Australia","institution_ids":["https://openalex.org/I78757542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100768356","display_name":"Juanjuan Xu","orcid":"https://orcid.org/0000-0003-0331-9976"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juanjuan Xu","raw_affiliation_strings":["School of Control Science and Engineering, Shandong University, Jinan, China"],"affiliations":[{"raw_affiliation_string":"School of Control Science and Engineering, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065677770","display_name":"Minyue Fu","orcid":"https://orcid.org/0000-0002-4659-601X"},"institutions":[{"id":"https://openalex.org/I78757542","display_name":"University of Newcastle Australia","ror":"https://ror.org/00eae9z71","country_code":"AU","type":"education","lineage":["https://openalex.org/I78757542"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Minyue Fu","raw_affiliation_strings":["School of Electrical Engineering and Computing, University of Newcastle, Callaghan, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"School of Electrical Engineering and Computing, University of Newcastle, Callaghan, NSW, Australia","institution_ids":["https://openalex.org/I78757542"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008453377"],"corresponding_institution_ids":["https://openalex.org/I78757542"],"apc_list":null,"apc_paid":null,"fwci":3.3177,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.92925122,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"52","issue":"9","first_page":"9170","last_page":"9178"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9969000220298767,"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/T12158","display_name":"Guidance and Control Systems","score":0.9692000150680542,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/nash-equilibrium","display_name":"Nash equilibrium","score":0.6131130456924438},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.5164928436279297},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.4882254898548126},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.46556994318962097},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.07699152827262878}],"concepts":[{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.6131130456924438},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.5164928436279297},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.4882254898548126},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.46556994318962097},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.07699152827262878}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005246","descriptor_name":"Feedback","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005246","descriptor_name":"Feedback","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005246","descriptor_name":"Feedback","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2021.3052832","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2021.3052832","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:33710965","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33710965","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":[{"display_name":"Peace, Justice and strong institutions","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3157209454","display_name":null,"funder_award_id":"2020QNQT016","funder_id":"https://openalex.org/F4320311026","funder_display_name":"Shandong University"},{"id":"https://openalex.org/G4379815246","display_name":null,"funder_award_id":"61922051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4525805536","display_name":null,"funder_award_id":"U1806204","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5523741472","display_name":null,"funder_award_id":"U1701264","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7152861903","display_name":null,"funder_award_id":"61633014","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7986487932","display_name":null,"funder_award_id":"61873332","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G812791822","display_name":null,"funder_award_id":"DP200103507","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320311026","display_name":"Shandong University","ror":"https://ror.org/0207yh398"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1495711302","https://openalex.org/W1643218028","https://openalex.org/W1972845749","https://openalex.org/W1976956127","https://openalex.org/W1991927580","https://openalex.org/W1995062574","https://openalex.org/W1995097018","https://openalex.org/W1999686056","https://openalex.org/W2005913866","https://openalex.org/W2007380427","https://openalex.org/W2019723559","https://openalex.org/W2055133653","https://openalex.org/W2087012571","https://openalex.org/W2107306424","https://openalex.org/W2141234504","https://openalex.org/W2141858721","https://openalex.org/W2147258494","https://openalex.org/W2151252227","https://openalex.org/W2165257315","https://openalex.org/W2345097924","https://openalex.org/W2550394442","https://openalex.org/W2790374560","https://openalex.org/W2807176303","https://openalex.org/W2887344203","https://openalex.org/W2897975793","https://openalex.org/W2946954414","https://openalex.org/W2954033048","https://openalex.org/W3047319512"],"related_works":["https://openalex.org/W2803931294","https://openalex.org/W2282604764","https://openalex.org/W2569414037","https://openalex.org/W2500870930","https://openalex.org/W2218535193","https://openalex.org/W4389370903","https://openalex.org/W2468739564","https://openalex.org/W1554758635","https://openalex.org/W4302558842","https://openalex.org/W2171981925"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3],"study":[4],"the":[5,10,21,26,34,41,52,56,62,71,77,91,94],"feedback":[6],"Nash":[7,64],"strategy":[8],"of":[9,33,76,93],"model-free":[11],"nonzero-sum":[12],"difference":[13],"game.":[14],"The":[15,66],"main":[16],"contribution":[17],"is":[18,38,44,49,68,87],"to":[19,51,69,89],"present":[20],"Q":[22,72],"-learning":[23],"algorithm":[24],"for":[25,61],"linear":[27],"quadratic":[28],"game":[29,43],"without":[30],"prior":[31],"knowledge":[32],"system":[35],"model.":[36],"It":[37],"noted":[39],"that":[40],"studied":[42],"in":[45,55,74],"finite":[46],"horizon":[47],"which":[48,58],"novel":[50],"learning":[53],"algorithms":[54],"literature":[57],"are":[59],"mostly":[60],"infinite-horizon":[63],"strategy.":[65],"key":[67],"characterize":[70],"-factors":[73],"terms":[75],"arbitrary":[78],"control":[79],"input":[80],"and":[81],"state":[82],"information.":[83],"A":[84],"numerical":[85],"example":[86],"given":[88],"verify":[90],"effectiveness":[92],"proposed":[95],"algorithm.":[96]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2021-03-15T00:00:00"}