{"id":"https://openalex.org/W4391022124","doi":"https://doi.org/10.1109/cdc49753.2023.10383431","title":"Model-Free Data-Driven Predictive Control Using Reinforcement Learning","display_name":"Model-Free Data-Driven Predictive Control Using Reinforcement Learning","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391022124","doi":"https://doi.org/10.1109/cdc49753.2023.10383431"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383431","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc49753.2023.10383431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5012590059","display_name":"Shambhuraj Sawant","orcid":null},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Shambhuraj Sawant","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076502958","display_name":"Dirk Reinhardt","orcid":"https://orcid.org/0000-0002-7027-4483"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Dirk Reinhardt","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033874726","display_name":"Arash Bahari Kordabad","orcid":"https://orcid.org/0000-0001-8931-5372"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Arash Bahari Kordabad","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049645185","display_name":"S\u00e9bastien Gros","orcid":"https://orcid.org/0000-0001-6054-2133"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Sebastien Gros","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204778367"],"apc_list":null,"apc_paid":null,"fwci":1.7535,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.86406558,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2","issue":null,"first_page":"4046","last_page":"4052"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9983999729156494,"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":0.9983999729156494,"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/T11236","display_name":"Control Systems and Identification","score":0.9930999875068665,"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":0.9905999898910522,"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/model-predictive-control","display_name":"Model predictive control","score":0.872635006904602},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8481878042221069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7244889736175537},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.692037045955658},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5722506046295166},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5507951974868774},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5032116770744324},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.502770185470581},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4970686733722687},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4642278552055359},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.44471031427383423},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.437829852104187},{"id":"https://openalex.org/keywords/system-identification","display_name":"System identification","score":0.43639686703681946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43014711141586304},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.42229220271110535},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35516858100891113},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.2682555317878723},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.18793824315071106},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1324942708015442},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1319183111190796}],"concepts":[{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.872635006904602},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8481878042221069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7244889736175537},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.692037045955658},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5722506046295166},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5507951974868774},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5032116770744324},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.502770185470581},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4970686733722687},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4642278552055359},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.44471031427383423},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.437829852104187},{"id":"https://openalex.org/C119247159","wikidata":"https://www.wikidata.org/wiki/Q1366192","display_name":"System identification","level":3,"score":0.43639686703681946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43014711141586304},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.42229220271110535},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35516858100891113},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2682555317878723},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.18793824315071106},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1324942708015442},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1319183111190796},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383431","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/cdc49753.2023.10383431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1531324864","https://openalex.org/W2112862244","https://openalex.org/W2615836285","https://openalex.org/W2810195925","https://openalex.org/W2930426397","https://openalex.org/W2948652605","https://openalex.org/W2992833799","https://openalex.org/W3119715644","https://openalex.org/W3138294267","https://openalex.org/W3153654730","https://openalex.org/W3185747626","https://openalex.org/W3198743568","https://openalex.org/W4200080422","https://openalex.org/W4214717370","https://openalex.org/W4225603049","https://openalex.org/W4285446252","https://openalex.org/W4294690657","https://openalex.org/W4312445281","https://openalex.org/W4313160026","https://openalex.org/W6684205842"],"related_works":["https://openalex.org/W1980381208","https://openalex.org/W1990079087","https://openalex.org/W2364594919","https://openalex.org/W2320156573","https://openalex.org/W1480508098","https://openalex.org/W2141538351","https://openalex.org/W2074116088","https://openalex.org/W2053946710","https://openalex.org/W1997118413","https://openalex.org/W1558935349"],"abstract_inverted_index":{"This":[0],"paper":[1,105],"proposes":[2],"a":[3,48,98,130],"novel":[4],"approach":[5,72,112,122],"for":[6,21,129],"Predictive":[7,81],"Control":[8,82],"utilizing":[9],"Reinforcement":[10],"Learning":[11],"(RL)":[12],"and":[13,33,84],"Data-Driven":[14],"techniques":[15],"to":[16,86,96,123],"derive":[17],"optimal":[18,44,126],"control":[19,39,45,127],"policies":[20],"real":[22,131],"systems.":[23],"Using":[24],"pure":[25],"input-output":[26],"multi-step":[27],"predictors":[28],"based":[29],"on":[30],"Subspace":[31],"Identification":[32],"RL":[34,85],"techniques,":[35],"the":[36,43,55,60,66,70,74,77,107,110,118],"resulting":[37],"predictive":[38],"scheme":[40],"can":[41],"approximate":[42],"policy":[46,128],"of":[47,65,69,76,100,109,120],"system":[49,62,132],"with":[50],"high":[51],"accuracy,":[52],"even":[53],"if":[54],"predictor":[56],"cannot":[57],"accurately":[58],"capture":[59],"true":[61],"dynamics.":[63,141],"One":[64],"key":[67],"contributions":[68],"proposed":[71,111],"is":[73],"extension":[75],"framework":[78],"connecting":[79],"Model":[80],"(MPC)":[83],"one":[87],"that":[88],"does":[89],"not":[90],"require":[91],"explicit":[92],"state-space":[93],"models,":[94],"nor":[95],"define":[97],"notion":[99],"state":[101],"at":[102],"all.":[103],"The":[104],"demonstrates":[106],"efficacy":[108],"through":[113],"an":[114,125],"illustrative":[115],"example,":[116],"highlighting":[117],"ability":[119],"our":[121],"provide":[124],"without":[133],"requiring":[134],"any":[135],"prior":[136],"knowledge":[137],"about":[138],"its":[139],"internal":[140]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
