{"id":"https://openalex.org/W4407614820","doi":"https://doi.org/10.1016/j.neucom.2025.129709","title":"Data-based discrete-time two-player zero-sum delayed game via policy iteration Q-learning Method","display_name":"Data-based discrete-time two-player zero-sum delayed game via policy iteration Q-learning Method","publication_year":2025,"publication_date":"2025-02-17","ids":{"openalex":"https://openalex.org/W4407614820","doi":"https://doi.org/10.1016/j.neucom.2025.129709"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2025.129709","doi":"https://doi.org/10.1016/j.neucom.2025.129709","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2025.129709","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-c","cwts-core","dongbi-b","doyens","jufo-2","ki-jl-2","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"},"volume":null,"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":null,"display_name":"Zongyang Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongyang Jiang","raw_affiliation_strings":["School of Mathematics, Harbin Institute of Technology, Harbin, 150001, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics, Harbin Institute of Technology, Harbin, 150001, PR China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haiying Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haiying Zhang","raw_affiliation_strings":["School of Mathematics, Harbin Institute of Technology, Harbin, 150001, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics, Harbin Institute of Technology, Harbin, 150001, PR China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080746874","display_name":"Yu Xiao","orcid":"https://orcid.org/0000-0003-0269-0474","observed_orcids":["https://orcid.org/0000-0003-0269-0474"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Xiao","raw_affiliation_strings":["School of Mathematics, Harbin Institute of Technology, Harbin, 150001, PR China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics, Harbin Institute of Technology, Harbin, 150001, PR China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":{"value":2670,"currency":"USD","value_usd":2670},"apc_paid":null,"fwci":2.079,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.85696118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"631","issue":null,"first_page":"129709","last_page":"129709"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9990000128746033,"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":0.9990000128746033,"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":0.0005000000237487257,"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/T10791","display_name":"Advanced Control Systems Optimization","score":9.999999747378752e-05,"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":0.8939999938011169},{"id":"https://openalex.org/keywords/data-driven-learning","display_name":"data-driven learning","score":0.5239999890327454},{"id":"https://openalex.org/keywords/delay-operator","display_name":"delay operator","score":0.7950000166893005},{"id":"https://openalex.org/keywords/q-function","display_name":"Q-function","score":0.5400000214576721},{"id":"https://openalex.org/keywords/banach-spaces","display_name":"Banach spaces","score":0.8920000195503235},{"id":"https://openalex.org/keywords/kantorovich-theorem","display_name":"Kantorovich theorem","score":0.8149999976158142},{"id":"https://openalex.org/keywords/algorithm-convergence","display_name":"algorithm convergence","score":0.7879999876022339},{"id":"https://openalex.org/keywords/drone-flight-control","display_name":"drone flight control","score":0.8230000138282776}],"concepts":[{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6498538255691528},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.6334248781204224},{"id":"https://openalex.org/C136356330","wikidata":"https://www.wikidata.org/wiki/Q156612","display_name":"Zero-sum game","level":3,"score":0.590097963809967},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5820913910865784},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5210666060447693},{"id":"https://openalex.org/C138328387","wikidata":"https://www.wikidata.org/wiki/Q5419308","display_name":"Example of a game without a value","level":5,"score":0.47193166613578796},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.38486248254776},{"id":"https://openalex.org/C73795354","wikidata":"https://www.wikidata.org/wiki/Q287618","display_name":"Sequential game","level":3,"score":0.3801068663597107},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35360977053642273},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.35258007049560547},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.337218701839447},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3253708779811859},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3210624158382416},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2455901801586151},{"id":"https://openalex.org/C155930848","wikidata":"https://www.wikidata.org/wiki/Q1069099","display_name":"Normal-form game","level":4,"score":0.23033779859542847},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.17306071519851685},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14504095911979675},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.12762042880058289},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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":1,"locations":[{"id":"doi:10.1016/j.neucom.2025.129709","doi":"https://doi.org/10.1016/j.neucom.2025.129709","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2025.129709","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","ccf-c","cwts-core","dongbi-b","doyens","jufo-2","ki-jl-2","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1530596433","https://openalex.org/W1680219837","https://openalex.org/W1919728628","https://openalex.org/W1993308628","https://openalex.org/W2005437559","https://openalex.org/W2007640554","https://openalex.org/W2013895638","https://openalex.org/W2024303516","https://openalex.org/W2035018355","https://openalex.org/W2037025184","https://openalex.org/W2039327053","https://openalex.org/W2047417907","https://openalex.org/W2050838777","https://openalex.org/W2082020199","https://openalex.org/W2082657448","https://openalex.org/W2086808696","https://openalex.org/W2087063454","https://openalex.org/W2101879828","https://openalex.org/W2112103082","https://openalex.org/W2134582887","https://openalex.org/W2147791539","https://openalex.org/W2286604276","https://openalex.org/W2314981175","https://openalex.org/W2327933814","https://openalex.org/W2462102501","https://openalex.org/W2467518411","https://openalex.org/W2580629550","https://openalex.org/W2581606339","https://openalex.org/W2727450595","https://openalex.org/W2765645862","https://openalex.org/W2807176303","https://openalex.org/W2809121899","https://openalex.org/W2897702175","https://openalex.org/W2964546405","https://openalex.org/W2981970936","https://openalex.org/W2982660641","https://openalex.org/W3163501229","https://openalex.org/W3196924932","https://openalex.org/W4214717370","https://openalex.org/W4361026739","https://openalex.org/W4367321457","https://openalex.org/W4377101750","https://openalex.org/W4385336407","https://openalex.org/W4387321441","https://openalex.org/W4399385294","https://openalex.org/W4400723679","https://openalex.org/W4402084073"],"related_works":["https://openalex.org/W3009014967","https://openalex.org/W2936756261","https://openalex.org/W2927025417","https://openalex.org/W4393219325","https://openalex.org/W7141467975","https://openalex.org/W4319835589","https://openalex.org/W2972128755","https://openalex.org/W2895095767","https://openalex.org/W4389636418","https://openalex.org/W4322577214"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-02-17T00:00:00"}