{"id":"https://openalex.org/W4401880651","doi":"https://doi.org/10.1109/icps59941.2024.10640031","title":"Deep reinforcement learning-based model predictive control of uncertain linear systems","display_name":"Deep reinforcement learning-based model predictive control of uncertain linear systems","publication_year":2024,"publication_date":"2024-05-12","ids":{"openalex":"https://openalex.org/W4401880651","doi":"https://doi.org/10.1109/icps59941.2024.10640031"},"language":"en","primary_location":{"id":"doi:10.1109/icps59941.2024.10640031","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icps59941.2024.10640031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems (ICPS)","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/A5108142474","display_name":"Pengcheng Hu","orcid":"https://orcid.org/0000-0001-7174-4216"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pengcheng Hu","raw_affiliation_strings":["University of Victoria,Department of Mechanical Engineering,Victoria,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria,Department of Mechanical Engineering,Victoria,Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100681904","display_name":"Xinyuan Cao","orcid":"https://orcid.org/0000-0002-8043-505X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyuan Cao","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation,Shanghai,China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083229405","display_name":"Kunwu Zhang","orcid":"https://orcid.org/0000-0002-2734-5813"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kunwu Zhang","raw_affiliation_strings":["University of Victoria,Department of Mechanical Engineering,Victoria,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria,Department of Mechanical Engineering,Victoria,Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028730873","display_name":"Yang Shi","orcid":"https://orcid.org/0000-0003-1337-5322"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yang Shi","raw_affiliation_strings":["University of Victoria,Department of Mechanical Engineering,Victoria,Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria,Department of Mechanical Engineering,Victoria,Canada","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2913,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.54777917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998000264167786,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9998000264167786,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9969000220298767,"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":0.9954000115394592,"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":0.8108733892440796},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.7408058643341064},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6400474309921265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4969034492969513},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4316468834877014},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3960351049900055},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3339926600456238}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8108733892440796},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.7408058643341064},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6400474309921265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4969034492969513},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4316468834877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3960351049900055},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3339926600456238}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icps59941.2024.10640031","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icps59941.2024.10640031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 7th International Conference on Industrial Cyber-Physical Systems (ICPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1880805667","https://openalex.org/W1978956894","https://openalex.org/W1981723834","https://openalex.org/W2006859604","https://openalex.org/W2107726111","https://openalex.org/W2123459560","https://openalex.org/W2131836176","https://openalex.org/W2145339207","https://openalex.org/W2537300304","https://openalex.org/W2738778707","https://openalex.org/W2774922731","https://openalex.org/W2930426397","https://openalex.org/W2948652605","https://openalex.org/W3100789280","https://openalex.org/W3138294267","https://openalex.org/W3139377883","https://openalex.org/W3212274512","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W4320489133","https://openalex.org/W4387914188","https://openalex.org/W6637967152","https://openalex.org/W6639233429","https://openalex.org/W6674884181","https://openalex.org/W6677916085","https://openalex.org/W6678474417","https://openalex.org/W6683113397","https://openalex.org/W6683195989","https://openalex.org/W6730641667","https://openalex.org/W6747473740","https://openalex.org/W6792155000","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W1990079087","https://openalex.org/W3202234113","https://openalex.org/W4306904969","https://openalex.org/W2101188133","https://openalex.org/W4248731570","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2556120871"],"abstract_inverted_index":{"This":[0],"paper":[1],"introduces":[2],"deep":[3],"reinforcement":[4],"learning":[5],"(DRL)-based":[6],"model":[7],"predictive":[8],"control":[9,104],"(MPC)":[10],"for":[11,97],"constrained":[12],"linear":[13],"systems":[14],"with":[15],"bounded":[16],"additive":[17],"disturbances.":[18],"The":[19],"essential":[20],"idea":[21],"of":[22,30,94],"this":[23],"work":[24],"lies":[25],"in":[26,56,79,132],"a":[27,91,111,133],"novel":[28],"integration":[29],"MPC":[31,40],"into":[32],"DRL.":[33],"In":[34],"the":[35,51,57,71,80,83,87,103,107,137],"proposed":[36,108],"method,":[37],"rigid":[38,116],"tube":[39,117],"is":[41],"utilized":[42],"to":[43,62,69,115,126],"obtain":[44],"predicted":[45,52],"state":[46],"and":[47,68,122,139],"action":[48],"sequences.":[49],"Then":[50],"sequences":[53],"are":[54,124],"employed":[55],"soft":[58],"actor-critic":[59],"(SAC)":[60],"algorithm":[61,85],"form":[63],"temporal":[64],"difference":[65],"(TD)":[66],"targets":[67,78],"update":[70],"policy":[72],"online.":[73],"By":[74],"utilizing":[75],"generated":[76],"TD":[77],"DRLMPC":[81],"framework,":[82],"SAC":[84],"improves":[86],"optimality":[88],"without":[89],"requiring":[90],"large":[92],"number":[93],"real":[95],"datasets":[96],"pre-training":[98],"while":[99],"ensuring":[100],"safety":[101],"during":[102],"process.":[105],"Moreover,":[106],"method":[109],"has":[110],"comparable":[112],"computational":[113],"complexity":[114],"MPC.":[118],"Finally,":[119],"numerical":[120],"simulations":[121],"comparisons":[123],"provided":[125],"demonstrate":[127],"that":[128],"our":[129],"framework":[130],"results":[131],"better":[134],"performance":[135],"at":[136],"cost":[138],"convergence.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}