{"id":"https://openalex.org/W1999686056","doi":"https://doi.org/10.1109/adprl.2014.7010629","title":"Model-free Q-learning over finite horizon for uncertain linear continuous-time systems","display_name":"Model-free Q-learning over finite horizon for uncertain linear continuous-time systems","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1999686056","doi":"https://doi.org/10.1109/adprl.2014.7010629","mag":"1999686056"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5100717012","display_name":"Hao Xu","orcid":"https://orcid.org/0000-0003-4130-7925"},"institutions":[{"id":"https://openalex.org/I96749437","display_name":"Texas A&M University \u2013 Corpus Christi","ror":"https://ror.org/01mrfdz82","country_code":"US","type":"education","lineage":["https://openalex.org/I96749437"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Xu","raw_affiliation_strings":["College of Science and Engineering, Texas A&M University-Corpus Christi, Corpus Christi, TX, USA","[College of Science and Engineering, Texas A&M University-Corpus Christi, Corpus Christi, TX, USA]"],"affiliations":[{"raw_affiliation_string":"College of Science and Engineering, Texas A&M University-Corpus Christi, Corpus Christi, TX, USA","institution_ids":["https://openalex.org/I96749437"]},{"raw_affiliation_string":"[College of Science and Engineering, Texas A&M University-Corpus Christi, Corpus Christi, TX, USA]","institution_ids":["https://openalex.org/I96749437"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078910343","display_name":"S. Jagannathan","orcid":"https://orcid.org/0000-0002-2310-3737"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Jagannathan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100717012"],"corresponding_institution_ids":["https://openalex.org/I96749437"],"apc_list":null,"apc_paid":null,"fwci":0.3561,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.60679326,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"43","issue":null,"first_page":"1","last_page":"6"},"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9621000289916992,"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":0.9478999972343445,"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/estimator","display_name":"Estimator","score":0.7813295125961304},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6110773682594299},{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.6001173853874207},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5741137862205505},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5599542260169983},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5458328127861023},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4957343339920044},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4903831481933594},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.480448454618454},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4800756573677063},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.4449783265590668},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.4361827075481415},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.42766374349594116},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4181336760520935},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4024047255516052},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3871566355228424},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.1863657534122467},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.1249505877494812},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.08800461888313293}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.7813295125961304},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6110773682594299},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6001173853874207},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5741137862205505},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5599542260169983},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5458328127861023},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4957343339920044},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4903831481933594},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.480448454618454},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4800756573677063},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.4449783265590668},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.4361827075481415},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.42766374349594116},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4181336760520935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4024047255516052},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3871566355228424},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1863657534122467},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.1249505877494812},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.08800461888313293},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","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/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","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/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/adprl.2014.7010629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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":20,"referenced_works":["https://openalex.org/W92805021","https://openalex.org/W627134521","https://openalex.org/W1162378864","https://openalex.org/W1572161815","https://openalex.org/W1601081659","https://openalex.org/W1980516134","https://openalex.org/W2005437559","https://openalex.org/W2007343403","https://openalex.org/W2011150195","https://openalex.org/W2017570421","https://openalex.org/W2024303516","https://openalex.org/W2087063454","https://openalex.org/W2098432798","https://openalex.org/W2100677568","https://openalex.org/W2164465592","https://openalex.org/W2166954959","https://openalex.org/W2487144912","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W6603762378"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W4285537323","https://openalex.org/W1932159282","https://openalex.org/W2090698372","https://openalex.org/W4383890581","https://openalex.org/W2965004901","https://openalex.org/W2921905705","https://openalex.org/W4233178034","https://openalex.org/W2003293420"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,24],"novel":[4],"optimal":[5,53,96],"control":[6,54,90],"over":[7],"finite":[8],"horizon":[9],"has":[10],"been":[11],"introduced":[12],"for":[13],"linear":[14],"continuous-time":[15],"systems":[16],"by":[17,40,58,72],"using":[18,41,59,73],"adaptive":[19],"dynamic":[20],"programming":[21],"(ADP).":[22],"First,":[23],"new":[25],"time-varying":[26],"Q-function":[27,35,61],"parameterization":[28],"and":[29,48,84],"its":[30],"estimator":[31,36],"are":[32,67,79],"introduced.":[33],"Subsequently,":[34],"is":[37,56],"tuned":[38],"online":[39],"both":[42],"Bellman":[43],"equation":[44],"in":[45],"integral":[46],"form":[47],"terminal":[49],"cost.":[50],"Eventually,":[51],"near":[52],"gain":[55],"obtained":[57],"the":[60,64,88,95,102,105],"estimator.":[62],"All":[63],"closed-loop":[65],"signals":[66],"shown":[68],"to":[69,94],"be":[70],"bounded":[71],"Lyapunov":[74],"stability":[75],"analysis":[76],"where":[77],"bounds":[78],"functions":[80],"of":[81,104],"initial":[82],"conditions":[83],"final":[85],"time":[86],"while":[87],"estimated":[89],"signal":[91],"converges":[92],"close":[93],"value.":[97],"The":[98],"simulation":[99],"results":[100],"illustrate":[101],"effectiveness":[103],"proposed":[106],"scheme.":[107]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}