{"id":"https://openalex.org/W4387914188","doi":"https://doi.org/10.1109/codit58514.2023.10284335","title":"Data-Driven Model Predictive Control Using Deep Double Expected Sarsa","display_name":"Data-Driven Model Predictive Control Using Deep Double Expected Sarsa","publication_year":2023,"publication_date":"2023-07-03","ids":{"openalex":"https://openalex.org/W4387914188","doi":"https://doi.org/10.1109/codit58514.2023.10284335"},"language":"en","primary_location":{"id":"doi:10.1109/codit58514.2023.10284335","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/codit58514.2023.10284335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 9th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://bia.unibz.it/esploro/outputs/conferenceProceeding/Data-Driven-Model-Predictive-Control-Using-Deep/991006685298701241","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015141503","display_name":"Hoomaan MoradiMaryamnegari","orcid":"https://orcid.org/0000-0002-0858-0420"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Hoomaan MoradiMaryamnegari","raw_affiliation_strings":["Free University of Bozen-Bolzano Faculty of Engineering,Bolzano,Italy","Free University of Bozen-Bolzano Faculty of Engineering, Bolzano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Free University of Bozen-Bolzano Faculty of Engineering,Bolzano,Italy","institution_ids":["https://openalex.org/I171543936"]},{"raw_affiliation_string":"Free University of Bozen-Bolzano Faculty of Engineering, Bolzano, Italy","institution_ids":["https://openalex.org/I171543936"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080554397","display_name":"Marco Frego","orcid":"https://orcid.org/0000-0003-2855-9052"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Frego","raw_affiliation_strings":["Free University of Bozen-Bolzano Faculty of Engineering,Bolzano,Italy","Free University of Bozen-Bolzano Faculty of Engineering, Bolzano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Free University of Bozen-Bolzano Faculty of Engineering,Bolzano,Italy","institution_ids":["https://openalex.org/I171543936"]},{"raw_affiliation_string":"Free University of Bozen-Bolzano Faculty of Engineering, Bolzano, Italy","institution_ids":["https://openalex.org/I171543936"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083668298","display_name":"Angelika Peer","orcid":"https://orcid.org/0000-0002-2896-9011"},"institutions":[{"id":"https://openalex.org/I171543936","display_name":"Free University of Bozen-Bolzano","ror":"https://ror.org/012ajp527","country_code":"IT","type":"education","lineage":["https://openalex.org/I171543936"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Angelika Peer","raw_affiliation_strings":["Free University of Bozen-Bolzano Faculty of Engineering,Bolzano,Italy","Free University of Bozen-Bolzano Faculty of Engineering, Bolzano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Free University of Bozen-Bolzano Faculty of Engineering,Bolzano,Italy","institution_ids":["https://openalex.org/I171543936"]},{"raw_affiliation_string":"Free University of Bozen-Bolzano Faculty of Engineering, Bolzano, Italy","institution_ids":["https://openalex.org/I171543936"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I171543936"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"345","last_page":"350"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9997000098228455,"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":0.9997000098228455,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9980999827384949,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9957000017166138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.694807231426239},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6707744598388672},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6469687819480896},{"id":"https://openalex.org/keywords/parameterized-complexity","display_name":"Parameterized complexity","score":0.6214812397956848},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.6022334098815918},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5280928015708923},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5037004351615906},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.48789048194885254},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.45553848147392273},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45273441076278687},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.44396060705184937},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.415314257144928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3991566300392151},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.36711516976356506},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3387986421585083},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2517626881599426},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19413256645202637},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08516532182693481}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694807231426239},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6707744598388672},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6469687819480896},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.6214812397956848},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6022334098815918},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5280928015708923},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5037004351615906},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.48789048194885254},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.45553848147392273},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45273441076278687},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.44396060705184937},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.415314257144928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3991566300392151},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.36711516976356506},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3387986421585083},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2517626881599426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19413256645202637},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08516532182693481},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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":2,"locations":[{"id":"doi:10.1109/codit58514.2023.10284335","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/codit58514.2023.10284335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 9th International Conference on Control, Decision and Information Technologies (CoDIT)","raw_type":"proceedings-article"},{"id":"pmh:oai:alma.39UBZ_INST:11310898920001241","is_oa":true,"landing_page_url":"https://bia.unibz.it/esploro/outputs/conferenceProceeding/Data-Driven-Model-Predictive-Control-Using-Deep/991006685298701241","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"pmh:oai:alma.39UBZ_INST:11310898920001241","is_oa":true,"landing_page_url":"https://bia.unibz.it/esploro/outputs/conferenceProceeding/Data-Driven-Model-Predictive-Control-Using-Deep/991006685298701241","pdf_url":null,"source":{"id":"https://openalex.org/S4210197018","display_name":"View","issn_l":"2688-268X","issn":["2688-268X","2688-3988"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2535107243","https://openalex.org/W2930426397","https://openalex.org/W2948652605","https://openalex.org/W3136876223","https://openalex.org/W3138294267","https://openalex.org/W3156316153","https://openalex.org/W3185747626","https://openalex.org/W4200080422","https://openalex.org/W4212979410","https://openalex.org/W4289822971","https://openalex.org/W4294597284","https://openalex.org/W4296124382","https://openalex.org/W4299401133","https://openalex.org/W4312445281","https://openalex.org/W4313160026"],"related_works":["https://openalex.org/W2051058708","https://openalex.org/W1494268238","https://openalex.org/W154868527","https://openalex.org/W1983207144","https://openalex.org/W2490706771","https://openalex.org/W2480116122","https://openalex.org/W4255576661","https://openalex.org/W1516574938","https://openalex.org/W3021988786","https://openalex.org/W3099311996"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"a":[3,48,106,131,135],"data-driven":[4],"Model":[5],"Predictive":[6],"Controller":[7],"(MPC)":[8],"is":[9,24,40,51,63,82,166],"presented,":[10],"in":[11,99],"which":[12],"an":[13],"off-policy":[14],"Reinforcement":[15],"Learning":[16],"(RL)":[17],"method":[18],"called":[19],"Deep":[20],"Double":[21],"Expected":[22],"Sarsa":[23],"employed":[25],"to":[26,101,144,157,198],"update":[27],"the":[28,35,43,54,71,80,91,95,102,111,120,123,138,145,149,153,158,171,182,191,195,199],"weights":[29],"of":[30,70,122,137,152,178],"its":[31],"cost":[32,38,185],"function.":[33],"While":[34],"parameterized":[36],"MPC":[37,73,154],"function":[39,46,57],"used":[41,52],"as":[42,53,105],"current":[44],"action-value":[45,56],"estimator,":[47],"Neural":[49,61,139,200],"Network":[50,62,140,201],"subsequent":[55],"approximator.":[58],"The":[59,108],"target":[60,124],"trained":[64],"based":[65],"on":[66],"inputs":[67],"and":[68,147,175],"outputs":[69],"primary":[72],"obtained":[74],"at":[75],"previous":[76,159],"sampling":[77,87,160],"times,":[78],"whereby":[79],"training":[81,176],"performed":[83],"either":[84],"within":[85],"each":[86],"time":[88,92,116],"by":[89],"sharing":[90],"slots":[93],"with":[94,142],"main":[96,103],"algorithm":[97,104],"or":[98],"parallel":[100],"whole.":[107],"latter":[109,192],"reduces":[110],"required":[112],"real-time":[113,183],"computations":[114],"per":[115],"slot.":[117],"To":[118],"compute":[119],"action":[121],"policy,":[125],"two":[126],"strategies":[127],"are":[128],"employed:":[129],"Once":[130],"greedy":[132],"policy":[133],"using":[134],"minimization":[136],"model":[141],"respect":[143],"action,":[146],"once":[148],"second":[150],"element":[151],"vector":[155],"related":[156,197],"time.":[161],"Results":[162],"show":[163],"that":[164],"there":[165],"no":[167],"significant":[168],"difference":[169],"between":[170],"final":[172],"control":[173],"performance":[174],"speed":[177],"both":[179],"methods,":[180],"whereas":[181],"computational":[184],"can":[186,202],"be":[187,203],"significantly":[188],"reduced":[189],"for":[190],"approach":[193],"since":[194],"optimization":[196],"omitted.":[204]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}