{"id":"https://openalex.org/W7225196295","doi":"https://doi.org/10.48550/arxiv.2611.03540","title":"Reinforcement Twinning via Twin-Calibrated Bayesian Policy Search and Replay-Driven Identification","display_name":"Reinforcement Twinning via Twin-Calibrated Bayesian Policy Search and Replay-Driven Identification","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225196295","doi":"https://doi.org/10.48550/arxiv.2611.03540"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.03540","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03540","pdf_url":"https://arxiv.org/pdf/2611.03540","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.03540","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079885878","display_name":"Miguel A. Mendez","orcid":"https://orcid.org/0000-0002-1115-2187","observed_orcids":["https://orcid.org/0000-0002-1115-2187"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mendez, Miguel A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062558938","display_name":"Lorenzo Schena","orcid":"https://orcid.org/0000-0002-7183-0242","observed_orcids":["https://orcid.org/0000-0002-7183-0242"]},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]},{"id":"https://openalex.org/I149208984","display_name":"Von Karman Institute for Fluid Dynamics","ror":"https://ror.org/01r4bn552","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I149208984"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Schena, Lorenzo","raw_affiliation_strings":["Department of Mechanical Engineering , Vrije Universiteit Brussel (VUB) , 1050 Brussels , Belgium","Environmental and Applied Fluid Dynamics , von Karman Institute for Fluid Dynamics , 1640 Sint -Genesius-Rode , Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering , Vrije Universiteit Brussel (VUB) , 1050 Brussels , Belgium","institution_ids":["https://openalex.org/I13469542"]},{"raw_affiliation_string":"Environmental and Applied Fluid Dynamics , von Karman Institute for Fluid Dynamics , 1640 Sint -Genesius-Rode , Belgium","institution_ids":["https://openalex.org/I149208984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083945829","display_name":"Romain Poletti","orcid":"https://orcid.org/0000-0003-3566-6956","observed_orcids":["https://orcid.org/0000-0003-3566-6956"]},"institutions":[{"id":"https://openalex.org/I149208984","display_name":"Von Karman Institute for Fluid Dynamics","ror":"https://ror.org/01r4bn552","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I149208984"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Poletti, Romain","raw_affiliation_strings":["Environmental and Applied Fluid Dynamics , von Karman Institute for Fluid Dynamics , 1640 Sint -Genesius-Rode , Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Environmental and Applied Fluid Dynamics , von Karman Institute for Fluid Dynamics , 1640 Sint -Genesius-Rode , Belgium","institution_ids":["https://openalex.org/I149208984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114192993","display_name":"Y Lecomte","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]},{"id":"https://openalex.org/I149208984","display_name":"Von Karman Institute for Fluid Dynamics","ror":"https://ror.org/01r4bn552","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I149208984"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Lecomte, Yannick","raw_affiliation_strings":["Environmental and Applied Fluid Dynamics , von Karman Institute for Fluid Dynamics , 1640 Sint -Genesius-Rode , Belgium","SAAS , Universit\u00e9 libre de Bruxelles (ULB) , Av. Franklin Roosevelt 50 , 1050 Brussels , Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Environmental and Applied Fluid Dynamics , von Karman Institute for Fluid Dynamics , 1640 Sint -Genesius-Rode , Belgium","institution_ids":["https://openalex.org/I149208984"]},{"raw_affiliation_string":"SAAS , Universit\u00e9 libre de Bruxelles (ULB) , Av. Franklin Roosevelt 50 , 1050 Brussels , Belgium","institution_ids":["https://openalex.org/I132053463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146756351","display_name":"Sebastiano Randino","orcid":"https://orcid.org/0009-0001-9186-9371","observed_orcids":["https://orcid.org/0009-0001-9186-9371"]},"institutions":[{"id":"https://openalex.org/I132053463","display_name":"Universit\u00e9 Libre de Bruxelles","ror":"https://ror.org/01r9htc13","country_code":"BE","type":"education","lineage":["https://openalex.org/I132053463"]},{"id":"https://openalex.org/I149208984","display_name":"Von Karman Institute for Fluid Dynamics","ror":"https://ror.org/01r4bn552","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I149208984"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Randino, Sebastiano","raw_affiliation_strings":["Environmental and Applied Fluid Dynamics , von Karman Institute for Fluid Dynamics , 1640 Sint -Genesius-Rode , Belgium","SAAS , Universit\u00e9 libre de Bruxelles (ULB) , Av. Franklin Roosevelt 50 , 1050 Brussels , Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Environmental and Applied Fluid Dynamics , von Karman Institute for Fluid Dynamics , 1640 Sint -Genesius-Rode , Belgium","institution_ids":["https://openalex.org/I149208984"]},{"raw_affiliation_string":"SAAS , Universit\u00e9 libre de Bruxelles (ULB) , Av. Franklin Roosevelt 50 , 1050 Brussels , Belgium","institution_ids":["https://openalex.org/I132053463"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048451183","display_name":"Jan Van den Berghe","orcid":"https://orcid.org/0000-0001-9514-4928","observed_orcids":["https://orcid.org/0000-0001-9514-4928"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Berghe, Jan van den","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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/T11236","display_name":"Control Systems and Identification","score":0.5259000062942505,"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/T11236","display_name":"Control Systems and Identification","score":0.5259000062942505,"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":0.26829999685287476,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.03660000115633011,"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/digital-twin","display_name":"digital twin","score":0.6679999828338623},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5580000281333923},{"id":"https://openalex.org/keywords/model-identifiability","display_name":"model identifiability","score":0.6890000104904175},{"id":"https://openalex.org/keywords/kriging-surrogate-model","display_name":"Kriging surrogate model","score":0.6570000052452087},{"id":"https://openalex.org/keywords/model-discrepancy","display_name":"model mismatch","score":0.7979999780654907},{"id":"https://openalex.org/keywords/sparse-observations","display_name":"sparse observations","score":0.5379999876022339},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.7509999871253967},{"id":"https://openalex.org/keywords/gradient-based-refinement","display_name":"gradient-based refinement","score":0.8740000128746033},{"id":"https://openalex.org/keywords/wind-farm-control","display_name":"wind farm control","score":0.6110000014305115},{"id":"https://openalex.org/keywords/model-misspecification","display_name":"model misspecification","score":0.578000009059906},{"id":"https://openalex.org/keywords/data-driven-control","display_name":"data-driven control","score":0.46399998664855957}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7063999772071838},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.605400025844574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5720000267028809},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5608999729156494},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4480000138282776},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4456999897956848},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3864000141620636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3368000090122223},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C10485038","wikidata":"https://www.wikidata.org/wiki/Q48996162","display_name":"Hyperparameter optimization","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C126661757","wikidata":"https://www.wikidata.org/wiki/Q4925641","display_name":"Random search","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C119247159","wikidata":"https://www.wikidata.org/wiki/Q1366192","display_name":"System identification","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.2623000144958496}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.03540","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03540","pdf_url":"https://arxiv.org/pdf/2611.03540","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.2611.03540","doi":"https://doi.org/10.48550/arxiv.2611.03540","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.03540","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.03540","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03540","pdf_url":"https://arxiv.org/pdf/2611.03540","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":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.4943999946117401}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321390","display_name":"Fonds De La Recherche Scientifique - FNRS","ror":"https://ror.org/03q83t159"},{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320334840","display_name":"Fonds pour la Formation \u00e0 la Recherche dans l\u2019Industrie et dans l\u2019Agriculture","ror":"https://ror.org/03q83t159"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225196295.pdf","grobid_xml":"https://content.openalex.org/works/W7225196295.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4401560048","https://openalex.org/W4406133546","https://openalex.org/W7171768395","https://openalex.org/W7165962962","https://openalex.org/W4417090787","https://openalex.org/W4402260883","https://openalex.org/W7224115657","https://openalex.org/W7168155825","https://openalex.org/W4313291242","https://openalex.org/W7202192194"],"abstract_inverted_index":{"The":[0,112,150,232],"feasibility":[1],"of":[2,8,58,158,190],"updating":[3],"and":[4,38,127,182,244,252],"synchronising":[5],"digital":[6],"twins":[7],"actuated":[9],"systems":[10],"from":[11,75,194],"operational":[12],"data":[13,26],"depends":[14],"strongly":[15],"on":[16,24,118,154],"how":[17],"the":[18,25,59,63,84,97,103,119,175,186,204,222,229],"system":[19],"is":[20,100,152,201,207,250],"controlled":[21],"and,":[22],"consequently,":[23],"generated":[27],"during":[28],"operation.":[29],"This":[30,41,199],"establishes":[31],"a":[32,44,68,72,155,165,178,238],"direct":[33],"link":[34,50],"between":[35],"control":[36,160,245],"actuation":[37],"model":[39,168,253],"identifiability.":[40,149],"work":[42],"presents":[43],"reinforcement-twinning":[45],"framework":[46,151,239],"that":[47,99],"exploits":[48],"this":[49,110],"through":[51],"three":[52],"computational":[53],"components.":[54],"A":[55],"Gaussian-process":[56],"surrogate":[57],"physical":[60,114,197,248],"return":[61,173],"combines":[62],"twin":[64,85,120,176],"prediction,":[65],"used":[66],"as":[67,237],"calibrated":[69],"trend,":[70],"with":[71,124,136,164],"discrepancy":[73,254],"learned":[74],"measured":[76,106,216],"returns,":[77,217],"allowing":[78],"Bayesian":[79,134,192],"policy":[80,98,145,181],"search":[81,183,188,205],"to":[82,89,146,209,213],"exploit":[83],"without":[86],"being":[87],"tied":[88],"its":[90,128,195],"predictions.":[91],"Candidate":[92],"policies":[93,246],"are":[94,116,130,225],"proposed":[95],"around":[96],"optimal":[101],"for":[102,240],"twin,":[104],"while":[105],"returns":[107],"can":[108],"expand":[109,210],"region.":[111],"resulting":[113],"episodes":[115,141],"replayed":[117],"after":[121],"observer-based":[122],"synchronisation":[123],"sparse":[125],"measurements,":[126],"parameters":[129],"identified":[131],"by":[132,221,228],"combining":[133],"optimisation":[135,193],"gradient-based":[137],"refinement.":[138],"Selected":[139],"information-oriented":[140],"deploy":[142],"an":[143],"excitation":[144],"improve":[147],"parameter":[148],"demonstrated":[153],"Burgers-flow":[156],"analogue":[157],"dynamic-induction":[159],"in":[161,211,215],"wind":[162],"farms,":[163],"deliberately":[166],"misspecified":[167],"structure.":[169],"Despite":[170],"substantially":[171],"biased":[172],"predictions,":[174],"provides":[177],"useful":[179],"starting":[180],"region,":[184],"placing":[185],"guided":[187],"ahead":[189],"unguided":[191,230],"first":[196],"evaluations.":[198],"advantage":[200],"maintained":[202],"when":[203,247],"region":[206,224],"allowed":[208],"response":[212],"changes":[214],"whereas":[218],"searches":[219],"over-constrained":[220],"twin-defined":[223],"eventually":[226],"overtaken":[227],"alternatives.":[231],"results":[233],"support":[234],"reinforcement":[235],"twinning":[236],"jointly":[241],"adapting":[242],"models":[243],"interaction":[249],"limited":[251],"cannot":[255],"be":[256],"neglected.":[257]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}