{"id":"https://openalex.org/W7204087919","doi":"https://doi.org/10.48550/arxiv.2608.20858","title":"Sharing the Control Authority Between Deep Reinforcement Learning and Model Predictive Control: Application to Multi-Class Transportation Networks","display_name":"Sharing the Control Authority Between Deep Reinforcement Learning and Model Predictive Control: Application to Multi-Class Transportation Networks","publication_year":2026,"publication_date":"2026-08-21","ids":{"openalex":"https://openalex.org/W7204087919","doi":"https://doi.org/10.48550/arxiv.2608.20858"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.20858","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20858","pdf_url":"https://arxiv.org/pdf/2608.20858","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.20858","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024734260","display_name":"Giray \u00d6n\u00fcr","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Onur, Giray","raw_affiliation_strings":["Delft Center for Systems and Control , Delft University of Technology , Delft , 2628CD , The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control , Delft University of Technology , Delft , 2628CD , The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022595935","display_name":"Azita Dabiri","orcid":"https://orcid.org/0000-0002-4051-4896","observed_orcids":["https://orcid.org/0000-0002-4051-4896","https://orcid.org/0000-0002-1296-7580"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dabiri, Azita","raw_affiliation_strings":["Delft Center for Systems and Control , Delft University of Technology , Delft , 2628CD , The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control , Delft University of Technology , Delft , 2628CD , The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026547410","display_name":"Bart De Schutter","orcid":"https://orcid.org/0000-0001-9867-6196","observed_orcids":["https://orcid.org/0000-0001-9867-6196"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"De Schutter, Bart","raw_affiliation_strings":["Delft Center for Systems and Control , Delft University of Technology , Delft , 2628CD , The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control , Delft University of Technology , Delft , 2628CD , The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9429000020027161,"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/T10524","display_name":"Traffic control and management","score":0.9429000020027161,"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":0.02630000002682209,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.015300000086426735,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8550000190734863},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"model predictive control","score":1.0},{"id":"https://openalex.org/keywords/hybrid-control","display_name":"hybrid control","score":0.46000000834465027},{"id":"https://openalex.org/keywords/hierarchical-control","display_name":"hierarchical control","score":0.703000009059906},{"id":"https://openalex.org/keywords/freeway-traffic-control","display_name":"freeway traffic control","score":0.7730000019073486},{"id":"https://openalex.org/keywords/model-discrepancy","display_name":"model mismatch","score":0.871999979019165},{"id":"https://openalex.org/keywords/real-time-processing","display_name":"real-time processing","score":0.5170000195503235},{"id":"https://openalex.org/keywords/constraint-enforcement","display_name":"constraint enforcement","score":0.6489999890327454},{"id":"https://openalex.org/keywords/traffic-demand-uncertainty","display_name":"traffic demand uncertainty","score":0.5559999942779541}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7172999978065491},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.6942999958992004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769999861717224},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5835999846458435},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4578000009059906},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.39169999957084656},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3684999942779541},{"id":"https://openalex.org/C47796450","wikidata":"https://www.wikidata.org/wiki/Q508378","display_name":"Intelligent transportation system","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34700000286102295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3375000059604645},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.33410000801086426},{"id":"https://openalex.org/C114809511","wikidata":"https://www.wikidata.org/wiki/Q1412924","display_name":"Flow network","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C104122410","wikidata":"https://www.wikidata.org/wiki/Q1416406","display_name":"Network model","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C79487989","wikidata":"https://www.wikidata.org/wiki/Q934680","display_name":"Vehicle dynamics","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C118974865","wikidata":"https://www.wikidata.org/wiki/Q7300773","display_name":"Real-time Control System","level":3,"score":0.2678000032901764}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.20858","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20858","pdf_url":"https://arxiv.org/pdf/2608.20858","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.20858","doi":"https://doi.org/10.48550/arxiv.2608.20858","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.20858","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.20858","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.20858","pdf_url":"https://arxiv.org/pdf/2608.20858","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.7207000255584717,"display_name":"Industry, innovation and infrastructure"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204087919.pdf","grobid_xml":"https://content.openalex.org/works/W7204087919.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1757796397","https://openalex.org/W1978956894","https://openalex.org/W2017957151","https://openalex.org/W2065613509","https://openalex.org/W2132261755","https://openalex.org/W2494622204","https://openalex.org/W2515603563","https://openalex.org/W2619723897","https://openalex.org/W2794842204","https://openalex.org/W2904246096","https://openalex.org/W3022861755","https://openalex.org/W3032653400","https://openalex.org/W3042354433","https://openalex.org/W3092380111","https://openalex.org/W3100789280","https://openalex.org/W3112872849","https://openalex.org/W3121342653","https://openalex.org/W4297964528","https://openalex.org/W4310983607","https://openalex.org/W4320729567","https://openalex.org/W4323338647","https://openalex.org/W4362563547","https://openalex.org/W4362578042","https://openalex.org/W4390449235","https://openalex.org/W4390492434","https://openalex.org/W4408519626","https://openalex.org/W4410583140","https://openalex.org/W7128436456"],"related_works":["https://openalex.org/W4390492434","https://openalex.org/W7214889571","https://openalex.org/W7213530506","https://openalex.org/W6929110636","https://openalex.org/W4323650248","https://openalex.org/W3195505738","https://openalex.org/W2575961188","https://openalex.org/W2981402159","https://openalex.org/W4417298941","https://openalex.org/W4308427634"],"abstract_inverted_index":{"Transportation":[0],"networks,":[1],"in":[2,65],"particular":[3],"multi-class":[4,104,115,188],"transportation":[5,54,105,116],"networks":[6,8,67,117],"(i.e.,":[7],"with":[9,32,83,134,203,227],"mixed":[10],"vehicle":[11],"types),":[12],"are":[13,17],"complex":[14,100],"systems":[15,101],"that":[16,118,212],"challenging":[18],"to":[19,45],"control.":[20,56],"Recently,":[21],"Deep":[22],"Reinforcement":[23],"Learning":[24],"(DRL),":[25],"which":[26,40,95],"learns":[27],"control":[28,47,120,154,175],"policies":[29],"from":[30],"interactions":[31],"the":[33,142,148,169,213,217,228],"environment,":[34],"and":[35,61,75,124,131,138,151,172,196,206,232],"Model":[36],"Predictive":[37],"Control":[38],"(MPC),":[39],"uses":[41],"a":[42,110,187,192,197],"system":[43,59],"model":[44,132,204,239],"optimize":[46],"inputs,":[48],"have":[49],"been":[50],"increasingly":[51],"utilized":[52],"for":[53,99,114],"network":[55,93,190],"However,":[57],"nonlinear":[58],"dynamics":[60],"high-dimensional":[62],"state":[63],"spaces":[64],"large-scale":[66],"limit":[68],"DRL's":[69,127],"learning":[70],"capacity":[71],"under":[72,238],"time-constrained":[73],"training":[74],"increase":[76],"MPC's":[77,135],"computation":[78,130,163,224],"time,":[79,164],"hindering":[80],"real-time":[81],"implementation":[82],"limited":[84],"computational":[85],"resources.":[86],"Moreover,":[87],"MPC":[88,145,194,230],"depends":[89],"on":[90,186],"an":[91],"accurate":[92],"model,":[94],"is":[96,184],"often":[97],"unavailable":[98],"such":[102],"as":[103],"networks.":[106],"This":[107],"paper":[108],"proposes":[109],"novel":[111],"DRL-MPC":[112],"framework":[113,183,215],"divides":[119],"authority":[121],"between":[122],"DRL":[123,166],"MPC,":[125],"combining":[126],"fast":[128,179],"online":[129,180,223],"independence":[133],"built-in":[136],"optimization":[137],"constraint-handling":[139],"capabilities.":[140],"In":[141],"hierarchical":[143,193,229],"framework,":[144],"operates":[146,167],"at":[147,168],"higher":[149],"level":[150,171],"determines":[152,173],"low-frequency":[153],"inputs":[155,176],"whose":[156],"slower":[157],"update":[158],"rate":[159],"accommodates":[160],"its":[161,178],"high":[162],"while":[165],"lower":[170],"high-frequency":[174],"using":[177],"deployment.":[181],"The":[182],"evaluated":[185],"freeway":[189],"against":[191],"controller":[195],"hybrid":[198,218],"state-feedback-MPC":[199,219],"controller,":[200,220,231],"including":[201],"scenarios":[202],"mismatch":[205],"noisy":[207],"traffic":[208],"demands.":[209],"Results":[210],"show":[211],"proposed":[214],"outperforms":[216],"substantially":[221],"reduces":[222],"time":[225],"compared":[226],"provides":[233],"more":[234],"effective":[235],"constraint":[236],"enforcement":[237],"mismatch.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-25T00:00:00"}