{"id":"https://openalex.org/W2887843158","doi":"https://doi.org/10.1109/isie.2018.8433684","title":"Off-Policy Q-Learning for Infinite Horizon LQR Problem with Unknown Dynamics","display_name":"Off-Policy Q-Learning for Infinite Horizon LQR Problem with Unknown Dynamics","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2887843158","doi":"https://doi.org/10.1109/isie.2018.8433684","mag":"2887843158"},"language":"en","primary_location":{"id":"doi:10.1109/isie.2018.8433684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isie.2018.8433684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 27th International Symposium on Industrial Electronics (ISIE)","raw_type":"proceedings-article"},"type":"conference-paper","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":["Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"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":false,"raw_author_name":"Zhihong Peng","raw_affiliation_strings":["Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","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":["Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Control and Decision of Complex Systems, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.3176,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.47988242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"258","last_page":"263"},"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":0.9921000003814697,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.8701086044311523},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.6483428478240967},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6425702571868896},{"id":"https://openalex.org/keywords/lti-system-theory","display_name":"LTI system theory","score":0.5700550675392151},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.5303120613098145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5243594646453857},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5165635347366333},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.4756300747394562},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4616609215736389},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4605945348739624},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.42862364649772644},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.41622787714004517},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41051578521728516},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.372395783662796},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3429206609725952},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.3116479814052582},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29836639761924744},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.29766473174095154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28513103723526},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.19750672578811646}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8701086044311523},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.6483428478240967},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6425702571868896},{"id":"https://openalex.org/C87698059","wikidata":"https://www.wikidata.org/wiki/Q1808960","display_name":"LTI system theory","level":3,"score":0.5700550675392151},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.5303120613098145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5243594646453857},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5165635347366333},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.4756300747394562},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4616609215736389},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4605945348739624},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.42862364649772644},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.41622787714004517},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41051578521728516},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.372395783662796},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3429206609725952},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.3116479814052582},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29836639761924744},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.29766473174095154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28513103723526},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.19750672578811646},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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/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:10.1109/isie.2018.8433684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isie.2018.8433684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE 27th International Symposium on Industrial Electronics (ISIE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1576452626","https://openalex.org/W1616818660","https://openalex.org/W1991927580","https://openalex.org/W2005437559","https://openalex.org/W2007640554","https://openalex.org/W2012451615","https://openalex.org/W2015076306","https://openalex.org/W2024303516","https://openalex.org/W2030854676","https://openalex.org/W2037025184","https://openalex.org/W2041866840","https://openalex.org/W2087063454","https://openalex.org/W2121863487","https://openalex.org/W2146382756","https://openalex.org/W2148439597","https://openalex.org/W2341171179","https://openalex.org/W2467518411","https://openalex.org/W2484646121","https://openalex.org/W2564717627","https://openalex.org/W2580629550","https://openalex.org/W2606378794","https://openalex.org/W2761756876","https://openalex.org/W2768907917","https://openalex.org/W2798534591","https://openalex.org/W2963609304","https://openalex.org/W3213472335","https://openalex.org/W4205326910","https://openalex.org/W4214717370","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2357975469","https://openalex.org/W2101748387","https://openalex.org/W3096874164","https://openalex.org/W4388236136","https://openalex.org/W2807018115","https://openalex.org/W4281812492","https://openalex.org/W3105579180","https://openalex.org/W2970347269","https://openalex.org/W2146763310"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3],"novel":[4],"online":[5],"Q-Iearning":[6,29,42,52,107],"approach":[7],"is":[8,77,89,98],"proposed":[9,28,106],"to":[10,43,100],"solve":[11],"the":[12,38,44,48,51,59,65,68,72,81,102,105,112,115],"Infinite":[13],"Horizon":[14],"Linear":[15],"Quadratic":[16],"Regulator":[17],"(IHLQR)":[18],"problem":[19],"for":[20],"continuous-time":[21],"(CT)":[22],"linear":[23],"time-invariant":[24],"(LMI)":[25],"systems.":[26],"The":[27],"algorithm":[30,53],"employing":[31],"off-policy":[32],"reinforcement":[33],"learning":[34,49],"(RL)":[35],"technology":[36],"improves":[37],"exploration":[39],"ability":[40],"of":[41,67,104,114],"state":[45],"space.":[46],"During":[47],"process,":[50],"can":[54,84],"be":[55,85],"implemented":[56],"just":[57,63],"using":[58],"data":[60,82],"sets":[61,83],"which":[62,88],"contains":[64],"information":[66],"behavior":[69],"policy":[70],"and":[71],"corresponding":[73],"system":[74],"state,":[75],"thus":[76],"data-":[78],"driven.":[79],"Moreover,":[80],"used":[86],"repeatedly,":[87],"computationally":[90],"efficient.":[91],"A":[92],"mild":[93],"condition":[94],"on":[95],"probing":[96],"noise":[97],"established":[99],"ensure":[101],"converge":[103],"algorithm.":[108,117],"Simulation":[109],"results":[110],"demonstrate":[111],"effectiveness":[113],"developed":[116]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}