{"id":"https://openalex.org/W4413393645","doi":"https://doi.org/10.23919/acc63710.2025.11107979","title":"Hybrid Reinforcement Learning for Continuous-Time Industrial Systems with Time-Varying Delays","display_name":"Hybrid Reinforcement Learning for Continuous-Time Industrial Systems with Time-Varying Delays","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413393645","doi":"https://doi.org/10.23919/acc63710.2025.11107979"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107979","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 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/A5114286438","display_name":"Iga Pawlak","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Iga Pawlak","raw_affiliation_strings":["ABB Corporate Research,Västerås,Sweden"],"affiliations":[{"raw_affiliation_string":"ABB Corporate Research,Västerås,Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083670898","display_name":"Soroush Rastegarpour","orcid":"https://orcid.org/0000-0001-6639-7168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soroush Rastegarpour","raw_affiliation_strings":["ABB Corporate Research,Västerås,Sweden"],"affiliations":[{"raw_affiliation_string":"ABB Corporate Research,Västerås,Sweden","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038418293","display_name":"Hamid Reza Feyzmahdavian","orcid":"https://orcid.org/0000-0003-1149-4715"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hamid Reza Feyzmahdavian","raw_affiliation_strings":["ABB Corporate Research,Västerås,Sweden"],"affiliations":[{"raw_affiliation_string":"ABB Corporate Research,Västerås,Sweden","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105470811","display_name":"Alf Isaksson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alf J. Isaksson","raw_affiliation_strings":["ABB Corporate Research,Västerås,Sweden"],"affiliations":[{"raw_affiliation_string":"ABB Corporate Research,Västerås,Sweden","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114286438"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32315544,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"553","last_page":"558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.8363999724388123,"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"}},"topics":[{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.8363999724388123,"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":0.7405999898910522,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.7202000021934509,"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":0.7254421710968018},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6306724548339844},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3774317800998688},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3359818458557129},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.13885483145713806}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7254421710968018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6306724548339844},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3774317800998688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3359818458557129},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.13885483145713806}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc63710.2025.11107979","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1986278286","https://openalex.org/W2039984557","https://openalex.org/W2117864026","https://openalex.org/W2159566498","https://openalex.org/W3154264273","https://openalex.org/W3195689706","https://openalex.org/W4240729697","https://openalex.org/W4402298624","https://openalex.org/W4412658022"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Traditional":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"methods":[4,47],"typically":[5],"assume":[6],"that":[7,13,110],"actions":[8],"are":[9,37],"executed":[10],"instantly,":[11],"and":[12,23,35,52],"the":[14,99,115,121,137,141,144],"agent":[15,84,109,139],"receives":[16],"immediate":[17],"feedback":[18,36],"in":[19,27,32],"terms":[20],"of":[21,89,130,143],"state":[22],"reward":[24],"information.":[25],"However,":[26],"many":[28],"real-world":[29],"systems,":[30],"delays":[31],"action":[33],"execution":[34],"common,":[38],"making":[39],"these":[40],"assumptions":[41],"impractical.":[42],"While":[43],"some":[44],"existing":[45],"RL":[46,60],"address":[48],"scenarios":[49],"with":[50,133],"constant":[51],"known":[53],"delays,":[54,90],"this":[55],"paper":[56],"proposes":[57],"a":[58,78,82,94,107,127],"hybrid":[59],"approach":[61,70],"designed":[62],"to":[63,106],"handle":[64],"unknown":[65],"but":[66],"bounded":[67],"delays.":[68],"The":[69,118],"introduces":[71],"two":[72,122],"operational":[73],"modes,":[74],"each":[75],"managed":[76,125],"by":[77],"specialized":[79],"agent.":[80],"Initially,":[81],"delay-safe":[83],"guarantees":[85],"system":[86],"stability":[87],"regardless":[88],"ensuring":[91],"safety":[92],"during":[93],"delay":[95,100,145],"identification":[96],"phase.":[97],"Once":[98],"is":[101,104,124],"estimated,":[102],"control":[103],"transferred":[105],"delay-informed":[108,138],"optimizes":[111],"performance":[112],"based":[113],"on":[114,136],"identified":[116],"delay.":[117],"transition":[119],"between":[120],"agents":[123],"through":[126],"convex":[128],"combination":[129],"their":[131],"actions,":[132],"increasing":[134],"emphasis":[135],"as":[140],"accuracy":[142],"estimator":[146],"improves.":[147]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}