{"id":"https://openalex.org/W7213530506","doi":"https://doi.org/10.48550/arxiv.2609.17697","title":"Composite-Gradient Learning for Shared Control Authority Between Deep Reinforcement Learning and Model Predictive Control","display_name":"Composite-Gradient Learning for Shared Control Authority Between Deep Reinforcement Learning and Model Predictive Control","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7213530506","doi":"https://doi.org/10.48550/arxiv.2609.17697"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.17697","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17697","pdf_url":"https://arxiv.org/pdf/2609.17697","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/2609.17697","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":"\u00d6n\u00fcr, Giray","raw_affiliation_strings":["Delft Center for Systems and Control , Delft University of Technology , Delft , The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft Center for Systems and Control , Delft University of Technology , Delft , 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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dabiri, Azita","raw_affiliation_strings":["{g.oenuer ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"{g.oenuer ,","institution_ids":[]}]},{"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":[],"countries":[],"is_corresponding":false,"raw_author_name":"De Schutter, Bart","raw_affiliation_strings":["{g.oenuer ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"{g.oenuer ,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.5551999807357788,"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":0.5551999807357788,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.30320000648498535,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.08420000225305557,"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/deep-reinforcement-learning","display_name":"deep reinforcement learning","score":0.8730000257492065},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"model predictive control","score":1.0},{"id":"https://openalex.org/keywords/autonomous-systems","display_name":"autonomous systems","score":0.4650000035762787},{"id":"https://openalex.org/keywords/freeway-traffic-control","display_name":"freeway traffic control","score":0.7260000109672546},{"id":"https://openalex.org/keywords/control-policy-learning","display_name":"control policy learning","score":0.503000020980835}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7983999848365784},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.7770000100135803},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.625},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.5708000063896179},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.569100022315979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47859999537467957},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.39570000767707825},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3481000065803528},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3386000096797943},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.32019999623298645},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C155386361","wikidata":"https://www.wikidata.org/wiki/Q1649571","display_name":"Process control","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2694000005722046}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.17697","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17697","pdf_url":"https://arxiv.org/pdf/2609.17697","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.2609.17697","doi":"https://doi.org/10.48550/arxiv.2609.17697","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.17697","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:2609.17697","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.17697","pdf_url":"https://arxiv.org/pdf/2609.17697","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":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213530506.pdf","grobid_xml":"https://content.openalex.org/works/W7213530506.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W4391899943","https://openalex.org/W7204087919"],"related_works":["https://openalex.org/W2981402159","https://openalex.org/W4385451973","https://openalex.org/W1531349744","https://openalex.org/W2985764939","https://openalex.org/W4413394581","https://openalex.org/W6979373097","https://openalex.org/W4402836811","https://openalex.org/W3089418186","https://openalex.org/W4391022030","https://openalex.org/W4389649750"],"abstract_inverted_index":{"Integrated":[0],"deep":[1],"reinforcement":[2],"learning":[3,69,102,112],"(DRL)":[4],"and":[5,56,78,118,126,155,159],"model":[6,36],"predictive":[7],"control":[8,15,25,39,50,65,88,120,157,196],"(MPC)":[9],"methods":[10,165,201],"are":[11],"increasingly":[12],"used":[13],"to":[14,37,87],"autonomous":[16],"systems":[17],"by":[18,114],"combining":[19],"their":[20,129],"complementary":[21],"capabilities.":[22],"DRL":[23,54,94,117,134,154],"learns":[24,194],"policies":[26,197],"through":[27],"interaction":[28,91,130,151],"with":[29,48,92,147,163],"the":[30,53,57,64,76,93,107,111,116,133,153,172,199,212],"environment.":[31],"MPC":[32,58,72,108,119,156,168,179],"uses":[33],"a":[34,99,123,203],"system":[35],"optimize":[38],"inputs":[40,121,158],"while":[41],"accounting":[42,127],"for":[43,84,128],"constraints.":[44],"In":[45],"DRL-MPC":[46],"frameworks":[47],"shared":[49],"authority,":[51],"both":[52],"agent":[55,135],"controller":[59,109],"each":[60],"determine":[61],"part":[62,74,170],"of":[63,75,150,171,205],"inputs.":[66],"However,":[67],"common":[68],"formulations":[70],"treat":[71,167],"as":[73,122,169],"environment":[77,173],"therefore":[79],"do":[80],"not":[81],"explicitly":[82],"account":[83],"MPC's":[85],"contribution":[86],"or":[89,174],"its":[90],"agent.":[95],"This":[96],"paper":[97],"proposes":[98],"novel":[100],"composite-gradient":[101],"(CGL)":[103],"method":[104],"that":[105,166,175,185],"integrates":[106],"into":[110,180],"process":[113],"representing":[115],"joint":[124],"action":[125],"when":[131],"updating":[132],"during":[136],"training.":[137],"CGL":[138,186],"is":[139,161],"evaluated":[140],"on":[141],"two":[142],"multi-class":[143],"freeway":[144],"traffic":[145],"networks":[146],"different":[148],"strengths":[149],"between":[152],"it":[160],"compared":[162],"alternative":[164,200],"only":[176],"partially":[177],"incorporate":[178],"learning.":[181],"The":[182],"results":[183],"show":[184],"offers":[187],"limited":[188],"benefit":[189],"under":[190,208],"weak":[191],"interaction,":[192,210],"but":[193],"higher-performing":[195],"than":[198],"in":[202],"subset":[204],"training":[206],"runs":[207],"strong":[209],"although":[211],"average":[213],"control-performance":[214],"gains":[215],"remain":[216],"modest.":[217]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-18T00:00:00"}