{"id":"https://openalex.org/W2007399905","doi":"https://doi.org/10.1109/adprl.2014.7010632","title":"Reinforcement learning-based optimal control considering L computation time delay of linear discrete-time systems","display_name":"Reinforcement learning-based optimal control considering L computation time delay of linear discrete-time systems","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2007399905","doi":"https://doi.org/10.1109/adprl.2014.7010632","mag":"2007399905"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-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/A5110461146","display_name":"Taishi Fujita","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Taishi Fujita","raw_affiliation_strings":["Department of Cybernetics, Czech Technical University, Prague, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, Czech Technical University, Prague, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087421882","display_name":"Toshimitu Ushio","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Toshimitu Ushio","raw_affiliation_strings":["Department of Cybernetics, Czech Technical University, Prague, Czech Republic"],"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, Czech Technical University, Prague, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.463,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":4,"citation_normalized_percentile":{"value":0.602327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":79,"max":81},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9851,"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/T10040","display_name":"Adaptive Control of Nonlinear Systems","score":0.9843,"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/observer","display_name":"Observer (physics)","score":0.5417841}],"concepts":[{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.7169242},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7038867},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6976055},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.66485256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6486085},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.58367616},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5748593},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.5417841},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.50853646},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.41827404},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.38433206},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25030437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19298026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18813878},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13705575},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12938532},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010632","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":null,"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":31,"referenced_works":["https://openalex.org/W105751747","https://openalex.org/W1519369336","https://openalex.org/W1536220597","https://openalex.org/W1569320505","https://openalex.org/W1576452626","https://openalex.org/W1616818660","https://openalex.org/W177772893","https://openalex.org/W1868258070","https://openalex.org/W1949804828","https://openalex.org/W1983523797","https://openalex.org/W2010152647","https://openalex.org/W2072931156","https://openalex.org/W2085241251","https://openalex.org/W2098536261","https://openalex.org/W2101786389","https://openalex.org/W2113501460","https://openalex.org/W2117834624","https://openalex.org/W2121863487","https://openalex.org/W2127863965","https://openalex.org/W2134085869","https://openalex.org/W2151966330","https://openalex.org/W2158025740","https://openalex.org/W2163198877","https://openalex.org/W2165726932","https://openalex.org/W2476930474","https://openalex.org/W2623785075","https://openalex.org/W32403112","https://openalex.org/W4214717370","https://openalex.org/W4307347247","https://openalex.org/W560518094","https://openalex.org/W617710812"],"related_works":["https://openalex.org/W4391331176","https://openalex.org/W4380318855","https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W3084456289","https://openalex.org/W2138720691","https://openalex.org/W2032253950","https://openalex.org/W2024136090","https://openalex.org/W1991810297","https://openalex.org/W1819950161"],"abstract_inverted_index":{"In":[0,95],"embedded":[1],"control":[2,5,159,177,186,220,235],"systems,":[3],"the":[4,25,31,34,47,57,69,78,88,101,108,111,118,122,132,141,147,158,173,176,182,185,193,202,205,208,211,223,228,240],"input":[6,187],"is":[7,21,61,75,103,165,188],"computed":[8],"based":[9],"on":[10],"sensing":[11],"data":[12,35],"of":[13,68,90,110,124,146,169,172,192,204,210,236],"a":[14,17,22,65,71,104,170,218,237],"plant":[15,102,112,148,206,212],"in":[16,56,87],"processor":[18],"and":[19,33,151,175,243],"there":[20],"delay,":[23,28],"called":[24],"computation":[26,32,133],"time":[27,134],"due":[29],"to":[30,45,51,63,86,121,156,200,233],"transmission.":[36],"When":[37],"we":[38,43,98,116,139,180,216,226],"design":[39,89,123],"an":[40,91,125,198],"optimal":[41,93,127,162,231],"controller,":[42],"need":[44],"take":[46],"delay":[48,135],"into":[49,136],"account":[50],"achieve":[52],"its":[53,245],"optimality.":[54],"Moreover,":[55],"case":[58,142,183],"where":[59,143,184],"it":[60,152],"difficult":[62],"identify":[64],"mathematical":[66],"model":[67,72],"plant,":[70],"free":[73],"approach":[74,81,221],"useful.":[76],"Especially,":[77],"reinforcement":[79,119],"learning-based":[80],"has":[82],"been":[83],"much":[84],"attention":[85],"adaptive":[92,126,230],"controller.":[94],"this":[96],"paper,":[97],"assume":[99],"that":[100],"linear":[105],"system":[106],"but":[107],"parameters":[109,209],"are":[113,149,213],"unknown.":[114,214],"Then,":[115],"apply":[117,227],"learning":[120],"digital":[128],"controller":[129,232],"with":[130],"taking":[131],"consideration.":[137],"First,":[138],"consider":[140,181],"all":[144],"states":[145],"observed,":[150],"takes":[153],"L":[154],"times":[155],"update":[157],"input.":[160,178],"An":[161],"feedback":[163],"gain":[164],"learned":[166],"from":[167,190],"sequences":[168],"pair":[171],"state":[174,203,242],"Next,":[179],"determined":[189],"outputs":[191],"plant.":[194],"We":[195],"cannot":[196],"use":[197,217],"observer":[199],"estimate":[201],"since":[207],"So,":[215],"data-based":[219],"for":[222],"estimation.":[224],"Finally,":[225],"proposed":[229],"attitude":[234],"quadrotor":[238],"at":[239],"hovering":[241],"show":[244],"efficiency":[246],"by":[247],"simulation.":[248]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2007399905","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-01-06T12:29:13.447142","created_date":"2016-06-24"}