{"id":"https://openalex.org/W2917322258","doi":"https://doi.org/10.1109/jas.2019.1911390","title":"Reinforcement learning for linear continuous-time systems: an incremental learning approach","display_name":"Reinforcement learning for linear continuous-time systems: an incremental learning approach","publication_year":2019,"publication_date":"2019-02-25","ids":{"openalex":"https://openalex.org/W2917322258","doi":"https://doi.org/10.1109/jas.2019.1911390","mag":"2917322258"},"language":"en","primary_location":{"id":"doi:10.1109/jas.2019.1911390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jas.2019.1911390","pdf_url":null,"source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"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/CAA Journal of Automatica Sinica","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/A5028849529","display_name":"Tao Bian","orcid":"https://orcid.org/0000-0003-1661-2012"},"institutions":[{"id":"https://openalex.org/I100621029","display_name":"Bank of America","ror":"https://ror.org/006tvg625","country_code":"US","type":"other","lineage":["https://openalex.org/I100621029"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tao Bian","raw_affiliation_strings":["Bank of America Merrill Lynch, One Bryant Park, New York, NY 10036 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bank of America Merrill Lynch, One Bryant Park, New York, NY 10036 USA","institution_ids":["https://openalex.org/I100621029"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067046312","display_name":"Zhong\u2010Ping Jiang","orcid":"https://orcid.org/0000-0002-4868-9359"},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Ping Jiang","raw_affiliation_strings":["Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, 5 Metrotech Center, Brooklyn, NY 11201 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Control and Networks Lab, Department of Electrical and Computer Engineering, Tandon School of Engineering, New York University, 5 Metrotech Center, Brooklyn, NY 11201 USA","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.085,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.92195662,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"6","issue":"2","first_page":"433","last_page":"440"},"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":0.9944999814033508,"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":0.9922999739646912,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8362696170806885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6955389976501465},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.6043845415115356},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5544309020042419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.496634304523468},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4863501191139221},{"id":"https://openalex.org/keywords/online-machine-learning","display_name":"Online machine learning","score":0.4587123990058899},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.436368465423584},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.42617490887641907},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4095671474933624},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22404468059539795}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8362696170806885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6955389976501465},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.6043845415115356},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5544309020042419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.496634304523468},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4863501191139221},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.4587123990058899},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.436368465423584},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.42617490887641907},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4095671474933624},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22404468059539795},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jas.2019.1911390","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jas.2019.1911390","pdf_url":null,"source":{"id":"https://openalex.org/S2484288132","display_name":"IEEE/CAA Journal of Automatica Sinica","issn_l":"2329-9266","issn":["2329-9266","2329-9274"],"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/CAA Journal of Automatica Sinica","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":31,"referenced_works":["https://openalex.org/W55814457","https://openalex.org/W560518094","https://openalex.org/W755046805","https://openalex.org/W1507222174","https://openalex.org/W1520048352","https://openalex.org/W1520459220","https://openalex.org/W1578936488","https://openalex.org/W1925816294","https://openalex.org/W1998361253","https://openalex.org/W2017493230","https://openalex.org/W2050233777","https://openalex.org/W2073990179","https://openalex.org/W2094387729","https://openalex.org/W2101539915","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2122410182","https://openalex.org/W2139418546","https://openalex.org/W2147750403","https://openalex.org/W2148439597","https://openalex.org/W2155027007","https://openalex.org/W2164350703","https://openalex.org/W2331243380","https://openalex.org/W2467518411","https://openalex.org/W2543834468","https://openalex.org/W2570494446","https://openalex.org/W2727279496","https://openalex.org/W2766447205","https://openalex.org/W2963600139","https://openalex.org/W2995552585","https://openalex.org/W3183630977"],"related_works":["https://openalex.org/W1986633584","https://openalex.org/W2024191559","https://openalex.org/W2037866349","https://openalex.org/W2901581617","https://openalex.org/W184546935","https://openalex.org/W1976326851","https://openalex.org/W146740654","https://openalex.org/W4381996401","https://openalex.org/W2949717367","https://openalex.org/W4288327880"],"abstract_inverted_index":{"In":[0],"this":[1,51],"paper,":[2],"we":[3],"introduce":[4],"a":[5,30],"novel":[6],"reinforcement":[7],"learning":[8,20,24,38],"(RL)":[9],"scheme":[10],"for":[11],"linear":[12],"continuous-time":[13],"dynamical":[14],"systems.":[15],"Different":[16],"from":[17],"traditional":[18],"batch":[19],"algorithms,":[21],"an":[22],"incremental":[23],"approach":[25],"is":[26,62],"developed,":[27],"which":[28],"provides":[29],"more":[31],"efficient":[32],"way":[33],"to":[34,56,71],"tackle":[35],"the":[36,73],"on-line":[37],"problem":[39],"in":[40],"realworld":[41],"applications.":[42],"We":[43],"provide":[44],"concrete":[45],"convergence":[46],"and":[47],"robust":[48,58],"analysis":[49],"on":[50],"incremental-learning":[52],"algorithm.":[53],"An":[54],"extension":[55],"solving":[57],"optimal":[59],"control":[60],"problems":[61],"also":[63,69],"given.":[64],"Two":[65],"simulation":[66],"examples":[67],"are":[68],"given":[70],"illustrate":[72],"effectiveness":[74],"of":[75],"our":[76],"theoretical":[77],"result.":[78]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}