{"id":"https://openalex.org/W3120743337","doi":"https://doi.org/10.1109/icarcv50220.2020.9305458","title":"Higher-order Polynomial Signal Tracking Control of Unknown Systems using Off-policy Integral Reinforcement Learning","display_name":"Higher-order Polynomial Signal Tracking Control of Unknown Systems using Off-policy Integral Reinforcement Learning","publication_year":2020,"publication_date":"2020-12-13","ids":{"openalex":"https://openalex.org/W3120743337","doi":"https://doi.org/10.1109/icarcv50220.2020.9305458","mag":"3120743337"},"language":"en","primary_location":{"id":"doi:10.1109/icarcv50220.2020.9305458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv50220.2020.9305458","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":"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/A5038704515","display_name":"Weiran Cheng","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":true,"raw_author_name":"Weiran Cheng","raw_affiliation_strings":["School of Information and Control Engineering, Liaoning Shihua University, Liaoning, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Liaoning Shihua University, Liaoning, P.R. 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":"Jinna Li","raw_affiliation_strings":["School of Information and Control Engineering, Liaoning Shihua University, Liaoning, P.R. China"],"affiliations":[{"raw_affiliation_string":"School of Information and Control Engineering, Liaoning Shihua University, Liaoning, P.R. China","institution_ids":["https://openalex.org/I166846921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038704515"],"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":0.21433729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"41","issue":null,"first_page":"1077","last_page":"1081"},"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9634000062942505,"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"}},{"id":"https://openalex.org/T12277","display_name":"Frequency Control in Power Systems","score":0.95660001039505,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.7559311389923096},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5871115326881409},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5858700275421143},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5752739310264587},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.5684167146682739},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.5677950382232666},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5482509732246399},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.5114980936050415},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.46667373180389404},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4366473853588104},{"id":"https://openalex.org/keywords/control-signal","display_name":"Control signal","score":0.4297291934490204},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.42336559295654297},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.34051990509033203},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22610622644424438},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07411086559295654}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7559311389923096},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5871115326881409},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5858700275421143},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5752739310264587},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.5684167146682739},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5677950382232666},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5482509732246399},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5114980936050415},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.46667373180389404},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4366473853588104},{"id":"https://openalex.org/C3018134525","wikidata":"https://www.wikidata.org/wiki/Q2501541","display_name":"Control signal","level":3,"score":0.4297291934490204},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.42336559295654297},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34051990509033203},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22610622644424438},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07411086559295654},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/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/icarcv50220.2020.9305458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icarcv50220.2020.9305458","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":[{"score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"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":28,"referenced_works":["https://openalex.org/W13127292","https://openalex.org/W69446332","https://openalex.org/W113679202","https://openalex.org/W1538983743","https://openalex.org/W1614417283","https://openalex.org/W1616818660","https://openalex.org/W1967793246","https://openalex.org/W1972243698","https://openalex.org/W1976956127","https://openalex.org/W2003183707","https://openalex.org/W2010344625","https://openalex.org/W2012451615","https://openalex.org/W2020047580","https://openalex.org/W2024303516","https://openalex.org/W2055891887","https://openalex.org/W2087063454","https://openalex.org/W2088246243","https://openalex.org/W2094627939","https://openalex.org/W2097253853","https://openalex.org/W2098035803","https://openalex.org/W2113501460","https://openalex.org/W2139416664","https://openalex.org/W2148439597","https://openalex.org/W2151966330","https://openalex.org/W2887344203","https://openalex.org/W3043748799","https://openalex.org/W6602790046","https://openalex.org/W6632656698"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W2145775124"],"abstract_inverted_index":{"This":[0],"paper":[1],"aims":[2],"at":[3],"using":[4],"an":[5,28,37,71],"off-policy":[6,72],"integral":[7],"reinforcement":[8],"learning":[9],"(IRL)":[10],"algorithm":[11,74],"to":[12,77,101],"solve":[13,78],"the":[14,56,65,68,79,86,91,103,106],"linear":[15,42],"quadratic":[16],"tracking":[17,55],"(LQT)":[18],"control":[19,87,93],"problem":[20],"of":[21,54,67,105],"completely":[22],"unknown":[23,46],"continuous-time":[24,43],"systems,":[25],"such":[26],"that":[27],"arbitrary":[29],"higherorder":[30],"polynomial":[31],"signal":[32,58],"can":[33],"be":[34],"followed":[35],"via":[36],"optimal":[38,92],"approach.":[39,108],"Firstly,":[40],"a":[41,52,96],"system":[44],"with":[45,51,59],"model":[47],"matrices":[48],"is":[49,75,99],"introduced":[50],"target":[53],"reference":[57],"higher-order":[60],"polynomials.":[61],"Secondly,":[62],"based":[63],"on":[64],"knowledge":[66],"on-policy":[69],"IRL,":[70],"IRL":[73],"used":[76],"derived":[80],"iterative":[81],"Bellman":[82],"equation":[83],"and":[84],"update":[85],"policy":[88],"resulting":[89],"in":[90],"policy.":[94],"Finally,":[95],"simulation":[97],"example":[98],"given":[100],"show":[102],"efficiency":[104],"proposed":[107]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}