{"id":"https://openalex.org/W3119172216","doi":"https://doi.org/10.1109/icarcv50220.2020.9305479","title":"Data-driven tracking control approach for linear systems by on-policy Q-learning approach","display_name":"Data-driven tracking control approach for linear systems by on-policy Q-learning approach","publication_year":2020,"publication_date":"2020-12-13","ids":{"openalex":"https://openalex.org/W3119172216","doi":"https://doi.org/10.1109/icarcv50220.2020.9305479","mag":"3119172216"},"language":"en","primary_location":{"id":"doi:10.1109/icarcv50220.2020.9305479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv50220.2020.9305479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV)","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":null,"display_name":"Zhang Yihan","orcid":null},"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":false,"raw_author_name":"Zhang Yihan","raw_affiliation_strings":["M.S. degree in control engineering at Liaoning Shihua University, Fushun, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"M.S. degree in control engineering at Liaoning Shihua University, Fushun, China","institution_ids":["https://openalex.org/I166846921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057045555","display_name":"Zhenfei Xiao","orcid":null},"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":false,"raw_author_name":"Xiao Zhenfei","raw_affiliation_strings":["M.S. degree in control engineering at Liaoning Shihua University, Fushun, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"M.S. degree in control engineering at Liaoning Shihua University, Fushun, China","institution_ids":["https://openalex.org/I166846921"]}]},{"author_position":"last","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":false,"raw_author_name":"Li Jinna","raw_affiliation_strings":["professor with the School of Information and Control Engineering at Liaoning Shihua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"professor with the School of Information and Control Engineering at Liaoning Shihua University","institution_ids":["https://openalex.org/I166846921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I166846921"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26323687,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"50","issue":null,"first_page":"1066","last_page":"1070"},"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9922999739646912,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9718999862670898,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.7205848693847656},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.6485967636108398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6024727821350098},{"id":"https://openalex.org/keywords/realization","display_name":"Realization (probability)","score":0.5869265794754028},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5484354496002197},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.5419732928276062},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5215629935264587},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.510303258895874},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.48720425367355347},{"id":"https://openalex.org/keywords/tracking-system","display_name":"Tracking system","score":0.4815554916858673},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.47298893332481384},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.367445170879364},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.32731544971466064},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2879287302494049},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21715229749679565},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21248438954353333},{"id":"https://openalex.org/keywords/kalman-filter","display_name":"Kalman filter","score":0.10583722591400146}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7205848693847656},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.6485967636108398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6024727821350098},{"id":"https://openalex.org/C2781089630","wikidata":"https://www.wikidata.org/wiki/Q21856745","display_name":"Realization (probability)","level":2,"score":0.5869265794754028},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5484354496002197},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.5419732928276062},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5215629935264587},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.510303258895874},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.48720425367355347},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.4815554916858673},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.47298893332481384},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.367445170879364},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.32731544971466064},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2879287302494049},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21715229749679565},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21248438954353333},{"id":"https://openalex.org/C157286648","wikidata":"https://www.wikidata.org/wiki/Q846780","display_name":"Kalman filter","level":2,"score":0.10583722591400146},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icarcv50220.2020.9305479","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv50220.2020.9305479","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 16th International Conference on Control, Automation, Robotics and Vision (ICARCV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6452960226","display_name":null,"funder_award_id":"61673280,62073158","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1494800309","https://openalex.org/W1532040308","https://openalex.org/W1571637309","https://openalex.org/W1969959431","https://openalex.org/W1976956127","https://openalex.org/W1988076499","https://openalex.org/W1999213690","https://openalex.org/W2008684559","https://openalex.org/W2013895638","https://openalex.org/W2020047580","https://openalex.org/W2051377293","https://openalex.org/W2060686658","https://openalex.org/W2097253853","https://openalex.org/W2098035803","https://openalex.org/W2364209978","https://openalex.org/W2365852751","https://openalex.org/W2368450857","https://openalex.org/W2462102501","https://openalex.org/W2520794016","https://openalex.org/W2523345745","https://openalex.org/W2593469813","https://openalex.org/W2767696060","https://openalex.org/W2887344203","https://openalex.org/W2912832158","https://openalex.org/W2974120149","https://openalex.org/W2990022244","https://openalex.org/W3043748799","https://openalex.org/W6631567804","https://openalex.org/W6995487115"],"related_works":["https://openalex.org/W3192036299","https://openalex.org/W2146428417","https://openalex.org/W3176458675","https://openalex.org/W2561776955","https://openalex.org/W2138120972","https://openalex.org/W576983769","https://openalex.org/W2122087045","https://openalex.org/W1964869133","https://openalex.org/W2016812753","https://openalex.org/W2151337373"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"an":[3,19,104],"improved":[4],"tracking":[5,37,55,80,97,129],"control":[6],"approach":[7,32],"for":[8],"discrete-time":[9],"(DT)":[10],"linear":[11,83],"system.":[12],"It's":[13],"combining":[14],"the":[15,30,35,43,60,78,94,117,127,139,143,147,150],"on-policy":[16,112],"Q-learning":[17,113],"and":[18,50,126],"extended":[20,105],"state":[21,65,106,124],"space":[22,107],"formulation":[23],"of":[24,29,66,82,96,122,149],"systems.":[25],"The":[26],"main":[27],"merit":[28],"proposed":[31],"lies":[33],"in":[34,75],"optimal":[36,79,128,144],"controller":[38],"can":[39,131,137],"be":[40,73,132],"found":[41],"using":[42],"measured":[44,118],"augmented":[45],"variables":[46],"including":[47],"input,":[48],"output":[49],"their":[51],"past":[52],"values":[53],"together":[54],"errors":[56],"rather":[57],"than":[58],"utilizing":[59,116],"system":[61,84],"model":[62],"parameters":[63],"or":[64],"systems,":[67],"since":[68],"they":[69],"are":[70],"hard":[71],"to":[72,103],"available":[74],"practice.":[76],"First,":[77],"problem":[81,130],"is":[85,153],"formulated":[86],"as":[87],"minimizing":[88],"a":[89,98],"specific":[90],"cost":[91],"function":[92],"containing":[93],"objective":[95],"reference":[99,140],"signal":[100,141],"with":[101],"respect":[102],"realization.":[108],"Therefore,":[109],"we":[110],"present":[111],"method,":[114],"only":[115],"data":[119],"without":[120],"need":[121],"designing":[123],"observer,":[125],"solved,":[133],"which":[134],"under":[135],"consideration":[136],"track":[138],"via":[142],"approach.":[145],"Finally,":[146],"validity":[148],"simulation":[151],"results":[152],"proved.":[154]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}