{"id":"https://openalex.org/W7164567976","doi":"https://doi.org/10.1109/lra.2026.3703237","title":"One to Rule Them All: Reinforcement Learning Policy Selection With Closed-Loop Sensitivity","display_name":"One to Rule Them All: Reinforcement Learning Policy Selection With Closed-Loop Sensitivity","publication_year":2026,"publication_date":"2026-06-12","ids":{"openalex":"https://openalex.org/W7164567976","doi":"https://doi.org/10.1109/lra.2026.3703237"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2026.3703237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3703237","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-05666505","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066389295","display_name":"Andrea Pupa","orcid":"https://orcid.org/0000-0002-1861-6482"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Pupa","raw_affiliation_strings":["Department of Science and Methods of Engineering, University of Modena and Reggio Emilia, Modena, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1861-6482","affiliations":[{"raw_affiliation_string":"Department of Science and Methods of Engineering, University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057766674","display_name":"Alberto Dionigi","orcid":"https://orcid.org/0000-0003-0581-2086"},"institutions":[{"id":"https://openalex.org/I27483092","display_name":"University of Perugia","ror":"https://ror.org/00x27da85","country_code":"IT","type":"education","lineage":["https://openalex.org/I27483092"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alberto Dionigi","raw_affiliation_strings":["Department of Engineering, University of Perugia, Perugia, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0581-2086","affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Perugia, Perugia, Italy","institution_ids":["https://openalex.org/I27483092"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067595490","display_name":"Paolo Robuffo Giordano","orcid":"https://orcid.org/0000-0001-6919-7751"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Paolo Robuffo Giordano","raw_affiliation_strings":["CNRS, Inria, IRISA, University of Rennes, Rennes, France"],"raw_orcid":"https://orcid.org/0000-0001-6919-7751","affiliations":[{"raw_affiliation_string":"CNRS, Inria, IRISA, University of Rennes, Rennes, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I2802519937","https://openalex.org/I56067802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032100434","display_name":"Cristian Secchi","orcid":"https://orcid.org/0000-0002-2098-0099"},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Cristian Secchi","raw_affiliation_strings":["Department of Science and Methods of Engineering, University of Modena and Reggio Emilia, Modena, Italy"],"raw_orcid":"https://orcid.org/0000-0002-2098-0099","affiliations":[{"raw_affiliation_string":"Department of Science and Methods of Engineering, University of Modena and Reggio Emilia, Modena, Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016925926","display_name":"Gabriele Costante","orcid":"https://orcid.org/0000-0002-8417-9372"},"institutions":[{"id":"https://openalex.org/I27483092","display_name":"University of Perugia","ror":"https://ror.org/00x27da85","country_code":"IT","type":"education","lineage":["https://openalex.org/I27483092"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gabriele Costante","raw_affiliation_strings":["Department of Engineering, University of Perugia, Perugia, Italy"],"raw_orcid":"https://orcid.org/0000-0002-8417-9372","affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Perugia, Perugia, Italy","institution_ids":["https://openalex.org/I27483092"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74479936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"8","first_page":"9606","last_page":"9613"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8960000276565552,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8960000276565552,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.017999999225139618,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.01549999974668026,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.5582000017166138},{"id":"https://openalex.org/keywords/sensitivity","display_name":"Sensitivity (control systems)","score":0.5537999868392944},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.504800021648407},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3149999976158142},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.30709999799728394}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5582000017166138},{"id":"https://openalex.org/C21200559","wikidata":"https://www.wikidata.org/wiki/Q7451068","display_name":"Sensitivity (control systems)","level":2,"score":0.5537999868392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.536899983882904},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.504800021648407},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4823000133037567},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40139999985694885},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3149999976158142},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26989999413490295}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2026.3703237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3703237","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-05666505v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05666505","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Robotics and Automation Letters, 2026, pp.1-8. ⟨10.1109/LRA.2026.3703237⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-05666505v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05666505","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Robotics and Automation Letters, 2026, pp.1-8. ⟨10.1109/LRA.2026.3703237⟩","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4031895101070404}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"reinforcement":[1,127],"learning-based":[2],"control,":[3],"reliable":[4,175],"zero-shot":[5,176],"transfer":[6,177],"from":[7],"simulation":[8,162],"to":[9,27,35,58,73,79,91,98,106,120,134,151,178],"real":[10,140,165,180],"hardware":[11,39],"remains":[12],"a":[13,28,41,76,92,155,179],"major":[14],"open":[15],"challenge.":[16],"The":[17,142],"offline":[18],"training":[19],"phase":[20],"typically":[21],"produces":[22],"multiple":[23],"models,":[24,129],"each":[25],"corresponding":[26],"different":[29,126,131],"policy,":[30],"and":[31,123,133,164,186],"choosing":[32],"which":[33],"model":[34],"deploy":[36,59],"on":[37,139],"physical":[38,93],"is":[40,46,57],"critical":[42],"decision.":[43],"However,":[44],"there":[45],"no":[47],"established":[48],"methodology":[49],"for":[50,113,116],"this":[51],"selection":[52],"process.":[53],"A":[54],"common":[55],"practice":[56],"the":[60,64,80,83,108,117,121,147,171,188],"policy":[61,85,159],"that":[62,170],"achieves":[63],"highest":[65],"reward":[66],"in":[67],"simulation,":[68],"without":[69],"evaluating":[70],"its":[71],"robustness":[72],"uncertainties.":[74],"As":[75],"result,":[77],"due":[78],"sim-to-real":[81],"gap,":[82],"selected":[84],"may":[86],"perform":[87],"poorly":[88],"when":[89],"transferred":[90],"robotic":[94],"system,":[95],"potentially":[96],"leading":[97],"unsafe":[99,191],"or":[100],"undesirable":[101],"behavior.":[102],"This":[103],"work":[104],"proposes":[105],"exploit":[107],"notion":[109],"of":[110,125,158,190],"\u201cclosed-loop":[111],"sensitivity\u201d":[112],"applying":[114],"it,":[115],"first":[118],"time,":[119],"analysis":[122],"comparison":[124],"learning":[128],"i.e.,":[130],"policies,":[132],"estimate":[135],"their":[136],"expected":[137],"performance":[138],"hardware.":[141],"proposed":[143,172],"metric":[144],"captures":[145],"how":[146],"closed-loop":[148],"system":[149],"reacts":[150],"modeling":[152],"errors,":[153],"providing":[154],"quantitative":[156],"measure":[157],"robustness.":[160],"Both":[161],"results":[163],"world":[166],"experimental":[167],"campaigns":[168],"demonstrate":[169],"approach":[173],"enables":[174],"robot,":[181],"while":[182],"effectively":[183],"handling":[184],"uncertainties":[185],"reducing":[187],"risk":[189],"behaviors.":[192]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-06-13T00:00:00"}