{"id":"https://openalex.org/W4294691809","doi":"https://doi.org/10.23919/acc53348.2022.9867835","title":"A Reinforcement Learning-based Adaptive Time-Delay Control and Its Application to Robot Manipulators","display_name":"A Reinforcement Learning-based Adaptive Time-Delay Control and Its Application to Robot Manipulators","publication_year":2022,"publication_date":"2022-06-08","ids":{"openalex":"https://openalex.org/W4294691809","doi":"https://doi.org/10.23919/acc53348.2022.9867835"},"language":"en","primary_location":{"id":"doi:10.23919/acc53348.2022.9867835","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867835","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 American Control Conference (ACC)","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/A5020732596","display_name":"Seung\u2010Min Baek","orcid":"https://orcid.org/0000-0003-4591-6912"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Seungmin Baek","raw_affiliation_strings":["Pohang University of Science and Technology,Department of Convergence IT Engineering (CiTE),Pohang,South Korea,37673"],"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology,Department of Convergence IT Engineering (CiTE),Pohang,South Korea,37673","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088443453","display_name":"Jongchan Baek","orcid":"https://orcid.org/0000-0002-3098-9775"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongchan Baek","raw_affiliation_strings":["Pohang University of Science and Technology,Department of Convergence IT Engineering (CiTE),Pohang,South Korea,37673"],"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology,Department of Convergence IT Engineering (CiTE),Pohang,South Korea,37673","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037754847","display_name":"Jinsuk Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinsuk Choi","raw_affiliation_strings":["Pohang University of Science and Technology,Department of Convergence IT Engineering (CiTE),Pohang,South Korea,37673"],"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology,Department of Convergence IT Engineering (CiTE),Pohang,South Korea,37673","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069368669","display_name":"Soohee Han","orcid":"https://orcid.org/0000-0002-9831-3499"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Soohee Han","raw_affiliation_strings":["Pohang University of Science and Technology,Department of Electrical Engineering and Convergence IT Engineering(CiTE),Pohang,South Korea,37673"],"affiliations":[{"raw_affiliation_string":"Pohang University of Science and Technology,Department of Electrical Engineering and Convergence IT Engineering(CiTE),Pohang,South Korea,37673","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020732596"],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":1.3045,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.79119086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2722","last_page":"2729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9944999814033508,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9887999892234802,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7991626858711243},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7048329710960388},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.6344154477119446},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4995739459991455},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4906066954135895},{"id":"https://openalex.org/keywords/robot-manipulator","display_name":"Robot manipulator","score":0.4848686158657074},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.47511038184165955},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.4652489125728607},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4565545916557312},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.43981456756591797},{"id":"https://openalex.org/keywords/inertia","display_name":"Inertia","score":0.4224781095981598},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.34388935565948486},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21773570775985718},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21017757058143616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08276355266571045},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.06934699416160583}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7991626858711243},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7048329710960388},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.6344154477119446},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4995739459991455},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4906066954135895},{"id":"https://openalex.org/C2985527887","wikidata":"https://www.wikidata.org/wiki/Q1587588","display_name":"Robot manipulator","level":3,"score":0.4848686158657074},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.47511038184165955},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.4652489125728607},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4565545916557312},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.43981456756591797},{"id":"https://openalex.org/C110407247","wikidata":"https://www.wikidata.org/wiki/Q122508","display_name":"Inertia","level":2,"score":0.4224781095981598},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.34388935565948486},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21773570775985718},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21017757058143616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08276355266571045},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.06934699416160583},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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":2,"locations":[{"id":"doi:10.23919/acc53348.2022.9867835","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867835","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 American Control Conference (ACC)","raw_type":"proceedings-article"},{"id":"pmh:oai:oasis.postech.ac.kr:2014.oak/116843","is_oa":false,"landing_page_url":"https://oasis.postech.ac.kr/handle/2014.oak/116843","pdf_url":null,"source":{"id":"https://openalex.org/S4306401965","display_name":"Open Access System for Information Sharing (Pohang University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123900574","host_organization_name":"Pohang University of Science and Technology","host_organization_lineage":["https://openalex.org/I123900574"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1867303563","https://openalex.org/W1955880755","https://openalex.org/W1965778174","https://openalex.org/W1967566180","https://openalex.org/W1980620643","https://openalex.org/W1997561135","https://openalex.org/W1997612086","https://openalex.org/W2012560418","https://openalex.org/W2018257502","https://openalex.org/W2089434629","https://openalex.org/W2125429845","https://openalex.org/W2145339207","https://openalex.org/W2148070153","https://openalex.org/W2158121031","https://openalex.org/W2159417854","https://openalex.org/W2167054844","https://openalex.org/W2167808181","https://openalex.org/W2470482648","https://openalex.org/W2608224837","https://openalex.org/W2749412222","https://openalex.org/W2774706289","https://openalex.org/W2781726626","https://openalex.org/W2896033043","https://openalex.org/W2904246096","https://openalex.org/W2913709584","https://openalex.org/W3086019649","https://openalex.org/W3153844337","https://openalex.org/W3202359610","https://openalex.org/W4214717370","https://openalex.org/W6631190155","https://openalex.org/W6649689742","https://openalex.org/W6747473740","https://openalex.org/W6757592117","https://openalex.org/W6801680865"],"related_works":["https://openalex.org/W1505013685","https://openalex.org/W2613933697","https://openalex.org/W2257413708","https://openalex.org/W2168805453","https://openalex.org/W1925083093","https://openalex.org/W2794899516","https://openalex.org/W2366605900","https://openalex.org/W2567391447","https://openalex.org/W2171805906","https://openalex.org/W2947706655"],"abstract_inverted_index":{"This":[0],"study":[1],"proposes":[2],"an":[3],"innovative":[4],"reinforcement":[5],"learning-based":[6],"time-delay":[7,25,61],"control":[8,18,41,62,128,149,175],"(RL-TDC)":[9],"scheme":[10,42],"to":[11,104,171],"provide":[12,172],"more":[13,173],"intelligent,":[14],"timely,":[15],"and":[16,92,96],"aggressive":[17],"efforts":[19],"than":[20],"the":[21,55,60,67,76,82,85,99,107,121,126,143,158,165],"existing":[22],"simple-structured":[23],"adaptive":[24],"controls":[26],"(ATDCs)":[27],"that":[28,142,164],"are":[29,154],"well-known":[30],"for":[31,156],"achieving":[32],"good":[33],"tracking":[34,72,123,159],"performances":[35],"in":[36],"practical":[37],"applications.":[38],"The":[39],"proposed":[40,100,144],"adopts":[43],"a":[44,89,139],"state-of-the-art":[45],"RL":[46],"algorithm":[47],"called":[48],"soft":[49],"actor":[50],"critic":[51],"(SAC)":[52],"with":[53,88,138],"which":[54],"inertia":[56],"gain":[57],"matrix":[58],"of":[59,84],"is":[63,102,134,162,168],"adjusted":[64],"toward":[65],"maximizing":[66,157],"expected":[68],"return":[69],"obtained":[70],"from":[71,115],"errors":[73,113],"over":[74],"all":[75],"future":[77],"time":[78,109,116],"periods.":[79],"By":[80],"learning":[81],"dynamics":[83],"robot":[86,140],"manipulator":[87,141],"data-driven":[90],"approach,":[91],"capturing":[93],"its":[94],"intractable":[95],"complicated":[97],"phenomena,":[98],"RL-TDC":[101,145],"trained":[103],"effectively":[105],"suppress":[106],"inherent":[108],"delay":[110,117],"estimation":[111],"(TDE)":[112],"arising":[114],"control,":[118],"thereby":[119],"ensuring":[120],"best":[122],"performance":[124],"within":[125],"given":[127],"capacity":[129],"limits.":[130],"As":[131],"expected,":[132],"it":[133],"demonstrated":[135],"through":[136],"simulation":[137],"avoids":[146],"conservative":[147],"small":[148],"actions":[150],"when":[151],"large":[152],"ones":[153],"required,":[155],"performance.":[160],"It":[161],"observed":[163],"stability":[166],"condition":[167],"fully":[169],"exploited":[170],"effective":[174],"actions.":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}