{"id":"https://openalex.org/W2936756261","doi":"https://doi.org/10.1007/s11432-018-9602-1","title":"Policy iteration based Q-learning for linear nonzero-sum quadratic differential games","display_name":"Policy iteration based Q-learning for linear nonzero-sum quadratic differential games","publication_year":2019,"publication_date":"2019-04-02","ids":{"openalex":"https://openalex.org/W2936756261","doi":"https://doi.org/10.1007/s11432-018-9602-1","mag":"2936756261"},"language":"en","primary_location":{"id":"doi:10.1007/s11432-018-9602-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11432-018-9602-1","pdf_url":null,"source":{"id":"https://openalex.org/S4210218743","display_name":"Science China Information Sciences","issn_l":"1869-1919","issn":["1869-1919","1674-733X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science China Information Sciences","raw_type":"journal-article"},"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":"https://openalex.org/A5101733708","display_name":"Xinxing Li","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxing Li","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, 100081, China","State Key Laboratory of Intelligent Control and Decision of Complex System, Beijing, 100081, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Control and Decision of Complex System, Beijing, 100081, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055648384","display_name":"Zhihong Peng","orcid":"https://orcid.org/0000-0001-9430-8652"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhihong Peng","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, 100081, China","State Key Laboratory of Intelligent Control and Decision of Complex System, Beijing, 100081, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Control and Decision of Complex System, Beijing, 100081, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067702812","display_name":"Li Liang","orcid":"https://orcid.org/0000-0002-9106-9323"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Liang","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, 100081, China","State Key Laboratory of Intelligent Control and Decision of Complex System, Beijing, 100081, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"State Key Laboratory of Intelligent Control and Decision of Complex System, Beijing, 100081, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017187516","display_name":"Wenzhong Zha","orcid":"https://orcid.org/0000-0003-2718-5052"},"institutions":[{"id":"https://openalex.org/I2800372957","display_name":"China Electronics Technology Group Corporation","ror":"https://ror.org/0098hst83","country_code":"CN","type":"company","lineage":["https://openalex.org/I2800372957"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenzhong Zha","raw_affiliation_strings":["Information Science Academy, China Electronics Technology Group Corporation, Beijing, 100086, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Science Academy, China Electronics Technology Group Corporation, Beijing, 100086, China","institution_ids":["https://openalex.org/I2800372957"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055648384"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":1.9538,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.87263275,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"62","issue":"5","first_page":null,"last_page":null},"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":0.9829999804496765,"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":0.911300003528595,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8071915507316589},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.7355101108551025},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.6053024530410767},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5701770782470703},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5104643106460571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5061003565788269},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.47842270135879517},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4310992658138275},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4203823208808899},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4167178273200989},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.40074411034584045},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.23894432187080383},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.19984805583953857},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.13522547483444214}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8071915507316589},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.7355101108551025},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.6053024530410767},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5701770782470703},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5104643106460571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5061003565788269},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.47842270135879517},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4310992658138275},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4203823208808899},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4167178273200989},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.40074411034584045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.23894432187080383},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.19984805583953857},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.13522547483444214},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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":1,"locations":[{"id":"doi:10.1007/s11432-018-9602-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11432-018-9602-1","pdf_url":null,"source":{"id":"https://openalex.org/S4210218743","display_name":"Science China Information Sciences","issn_l":"1869-1919","issn":["1869-1919","1674-733X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science China Information Sciences","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1557517019","https://openalex.org/W1576452626","https://openalex.org/W1583799131","https://openalex.org/W1594802219","https://openalex.org/W1614417283","https://openalex.org/W1616818660","https://openalex.org/W1991927580","https://openalex.org/W1997603681","https://openalex.org/W2005229381","https://openalex.org/W2012451615","https://openalex.org/W2019338681","https://openalex.org/W2024303516","https://openalex.org/W2027856954","https://openalex.org/W2032631296","https://openalex.org/W2037025184","https://openalex.org/W2053849443","https://openalex.org/W2068328804","https://openalex.org/W2068949505","https://openalex.org/W2088246243","https://openalex.org/W2100276679","https://openalex.org/W2102933137","https://openalex.org/W2108383324","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2125256511","https://openalex.org/W2132468772","https://openalex.org/W2148439597","https://openalex.org/W2151852050","https://openalex.org/W2183137222","https://openalex.org/W2214884926","https://openalex.org/W2245501338","https://openalex.org/W2258956268","https://openalex.org/W2289227442","https://openalex.org/W2326180695","https://openalex.org/W2329356151","https://openalex.org/W2329769476","https://openalex.org/W2405379562","https://openalex.org/W2417679505","https://openalex.org/W2475651303","https://openalex.org/W2529203006","https://openalex.org/W2550394442","https://openalex.org/W2564717627","https://openalex.org/W2579592432","https://openalex.org/W2580629550","https://openalex.org/W2601100663","https://openalex.org/W2740197008","https://openalex.org/W2761756876","https://openalex.org/W2767784613","https://openalex.org/W2807176303","https://openalex.org/W3150098721","https://openalex.org/W3213472335","https://openalex.org/W4214717370","https://openalex.org/W4307347247"],"related_works":["https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W3096874164","https://openalex.org/W2357975469","https://openalex.org/W2937181779","https://openalex.org/W2145363145","https://openalex.org/W3168977894"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
