{"id":"https://openalex.org/W2887344203","doi":"https://doi.org/10.1109/tnnls.2018.2861945","title":"Off-Policy Interleaved $Q$ -Learning: Optimal Control for Affine Nonlinear Discrete-Time Systems","display_name":"Off-Policy Interleaved $Q$ -Learning: Optimal Control for Affine Nonlinear Discrete-Time Systems","publication_year":2018,"publication_date":"2018-09-26","ids":{"openalex":"https://openalex.org/W2887344203","doi":"https://doi.org/10.1109/tnnls.2018.2861945","mag":"2887344203","pmid":"https://pubmed.ncbi.nlm.nih.gov/30273155"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2018.2861945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2861945","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.research.manchester.ac.uk/portal/en/publications/offpolicy-interleaved-qlearning-optimal-control-for-affine-nonlinear-discretetime-systems(d563e4d4-5d74-461d-a164-a8eec9178445).html","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070599005","display_name":"Jinna Li","orcid":"https://orcid.org/0000-0001-9985-6308"},"institutions":[{"id":"https://openalex.org/I166846921","display_name":"Liaoning Shihua University","ror":"https://ror.org/00k6c4h29","country_code":"CN","type":"education","lineage":["https://openalex.org/I166846921"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinna Li","raw_affiliation_strings":["School of Information and Control Engineering, Liaoning Shihua University, Fushun, China"],"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Liaoning Shihua University, Fushun, China","institution_ids":["https://openalex.org/I166846921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042520521","display_name":"Tianyou Chai","orcid":"https://orcid.org/0000-0002-4623-1483"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyou Chai","raw_affiliation_strings":["International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["UTA Research Institute, the University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, the University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086465750","display_name":"Zhengtao Ding","orcid":"https://orcid.org/0000-0003-0690-7853"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhengtao Ding","raw_affiliation_strings":["School of Electrical and Electronic Engineering, The University of Manchester, Manchester, U.K"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, The University of Manchester, Manchester, U.K","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100396295","display_name":"Yi Jiang","orcid":"https://orcid.org/0000-0001-8927-0119"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Jiang","raw_affiliation_strings":["International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070599005"],"corresponding_institution_ids":["https://openalex.org/I166846921"],"apc_list":null,"apc_paid":null,"fwci":12.5911,"has_fulltext":true,"cited_by_count":138,"citation_normalized_percentile":{"value":0.99039946,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"30","issue":"5","first_page":"1308","last_page":"1320"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":1.0,"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":1.0,"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":0.9778000116348267,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9772999882698059,"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/affine-transformation","display_name":"Affine transformation","score":0.7446280717849731},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6771148443222046},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.6094850897789001},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5754528641700745},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5449321866035461},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5002682209014893},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4425409734249115},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.44099557399749756},{"id":"https://openalex.org/keywords/discrete-time-and-continuous-time","display_name":"Discrete time and continuous time","score":0.41870272159576416},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4176492989063263},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.41684603691101074},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41282209753990173},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.40632379055023193},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3695145845413208},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3301423192024231},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30508238077163696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20603233575820923}],"concepts":[{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.7446280717849731},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6771148443222046},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.6094850897789001},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5754528641700745},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5449321866035461},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5002682209014893},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4425409734249115},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.44099557399749756},{"id":"https://openalex.org/C55689738","wikidata":"https://www.wikidata.org/wiki/Q15963867","display_name":"Discrete time and continuous time","level":2,"score":0.41870272159576416},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4176492989063263},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41684603691101074},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41282209753990173},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40632379055023193},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3695145845413208},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3301423192024231},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30508238077163696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20603233575820923},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tnnls.2018.2861945","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2861945","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:30273155","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30273155","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 neural networks and learning systems","raw_type":null},{"id":"pmh:oai:pure.atira.dk:publications/d563e4d4-5d74-461d-a164-a8eec9178445","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.research.manchester.ac.uk/portal/en/publications/offpolicy-interleaved-qlearning-optimal-control-for-affine-nonlinear-discretetime-systems(d563e4d4-5d74-461d-a164-a8eec9178445).html","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.atira.dk:publications/d563e4d4-5d74-461d-a164-a8eec9178445","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/d563e4d4-5d74-461d-a164-a8eec9178445","pdf_url":"https://www.research.manchester.ac.uk/portal/en/publications/offpolicy-interleaved-qlearning-optimal-control-for-affine-nonlinear-discretetime-systems(d563e4d4-5d74-461d-a164-a8eec9178445).html","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Li, J, Chai, T, Lewis, F W, Ding, Z & Jiang, Y 2018, 'Off-policy interleaved Q-learning: optimal control for affine nonlinear discrete-time systems', IEEE Transactions on NEural Networks and Learning Systems. https://doi.org/10.1109/TNNLS.2018.2861945","raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/d563e4d4-5d74-461d-a164-a8eec9178445","is_oa":true,"landing_page_url":null,"pdf_url":"https://www.research.manchester.ac.uk/portal/en/publications/offpolicy-interleaved-qlearning-optimal-control-for-affine-nonlinear-discretetime-systems(d563e4d4-5d74-461d-a164-a8eec9178445).html","source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1474490597","display_name":null,"funder_award_id":"111 Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3951694549","display_name":null,"funder_award_id":"N160804001","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4020255992","display_name":null,"funder_award_id":"Project","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4148739412","display_name":null,"funder_award_id":"201603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G476718691","display_name":null,"funder_award_id":"71602124","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5156944241","display_name":null,"funder_award_id":"61525302","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5409562055","display_name":null,"funder_award_id":"B08015","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"},{"id":"https://openalex.org/G5760752404","display_name":null,"funder_award_id":"Projects","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7033253288","display_name":null,"funder_award_id":"Grants","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7272473876","display_name":null,"funder_award_id":"61590922","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G74425646","display_name":null,"funder_award_id":"61673280","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7465081181","display_name":null,"funder_award_id":"2017006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7608752429","display_name":null,"funder_award_id":"Talent","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7836423780","display_name":null,"funder_award_id":"Liaoning","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8743717570","display_name":null,"funder_award_id":"61503257","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320311306","display_name":"University of Texas at Arlington","ror":"https://ror.org/019kgqr73"},{"id":"https://openalex.org/F4320320291","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320323191","display_name":"Nanjing University of Science and Technology","ror":"https://ror.org/00xp9wg62"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"},{"id":"https://openalex.org/F4320327041","display_name":"Ngee Ann Polytechnic","ror":"https://ror.org/01w953x65"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null},{"id":"https://openalex.org/F4320328262","display_name":"International Federation of Automatic Control","ror":null},{"id":"https://openalex.org/F4320335661","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2887344203.pdf"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W166862392","https://openalex.org/W560518094","https://openalex.org/W1488674906","https://openalex.org/W1972044154","https://openalex.org/W1972941473","https://openalex.org/W1988707322","https://openalex.org/W1991119064","https://openalex.org/W2002260889","https://openalex.org/W2005437559","https://openalex.org/W2012451615","https://openalex.org/W2013895638","https://openalex.org/W2029661056","https://openalex.org/W2041866840","https://openalex.org/W2048687352","https://openalex.org/W2087063454","https://openalex.org/W2105004188","https://openalex.org/W2147750403","https://openalex.org/W2148439597","https://openalex.org/W2152161277","https://openalex.org/W2165726932","https://openalex.org/W2462102501","https://openalex.org/W2560131027","https://openalex.org/W2564717627","https://openalex.org/W2580629550","https://openalex.org/W2605603065","https://openalex.org/W2606378794","https://openalex.org/W2609750639","https://openalex.org/W2727279496","https://openalex.org/W2758863483","https://openalex.org/W2761756876","https://openalex.org/W2762709466","https://openalex.org/W2767696060","https://openalex.org/W2771641782","https://openalex.org/W2801899875","https://openalex.org/W2963674921","https://openalex.org/W3213472335","https://openalex.org/W4233696721","https://openalex.org/W6715102896","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W2742483371","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W3087814763","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W4376605461","https://openalex.org/W4400868993","https://openalex.org/W2361647908","https://openalex.org/W2952356279"],"abstract_inverted_index":{"In":[0],"this":[1,50],"paper,":[2],"a":[3,100,150],"novel":[4,151],"off-policy":[5,39,110,152],"interleaved":[6,142,153],"Q-learning":[7,53,97,111,143,154],"algorithm":[8,117,155],"is":[9,63,69,91,104,156,161],"presented":[10],"for":[11,55,87],"solving":[12],"optimal":[13,47,56,124],"control":[14,57,102,125],"problem":[15,126],"of":[16,34,58,74,116,121,171],"affine":[17,59],"nonlinear":[18,32,60],"discrete-time":[19],"(DT)":[20],"systems,":[21,35],"using":[22,95],"only":[23],"the":[24,28,114,141,146,169,172],"measured":[25],"data":[26],"along":[27],"system":[29],"trajectories.":[30],"Affine":[31],"feature":[33],"unknown":[36],"dynamics,":[37],"and":[38,66,118,158],"learning":[40],"approach":[41,144],"pose":[42],"tremendous":[43],"challenges":[44],"on":[45],"approximating":[46],"controllers.":[48],"To":[49],"end,":[51],"on-policy":[52,96],"method":[54],"DT":[61],"systems":[62,86,132],"reviewed":[64],"first,":[65],"its":[67,159],"convergence":[68,115,160],"rigorously":[70],"proven.":[71,162],"The":[72],"bias":[73,120],"solution":[75,122],"to":[76,85,123,131,167],"Q-function-based":[77],"Bellman":[78],"equation":[79],"caused":[80],"by":[81,107,140],"adding":[82,128],"probing":[83,129],"noises":[84],"satisfying":[88],"persistent":[89],"excitation":[90],"also":[92],"analyzed":[93],"when":[94,127],"approach.":[98],"Then,":[99],"behavior":[101],"policy":[103],"introduced":[105],"followed":[106],"proposing":[108],"an":[109],"algorithm.":[112],"Meanwhile,":[113],"no":[119],"noise":[130],"are":[133,165],"investigated.":[134],"Third,":[135],"three":[136],"neural":[137],"networks":[138],"run":[139],"in":[145],"actor-critic":[147],"framework.":[148],"Thus,":[149],"derived,":[157],"Simulation":[163],"results":[164],"given":[166],"verify":[168],"effectiveness":[170],"proposed":[173],"method.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":20},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":30},{"year":2019,"cited_by_count":16},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}