{"id":"https://openalex.org/W4410949714","doi":"https://doi.org/10.1109/tac.2025.3575565","title":"Risk-Sensitive Safety Filters for Reinforcement Learning With Probabilistic Guarantees","display_name":"Risk-Sensitive Safety Filters for Reinforcement Learning With Probabilistic Guarantees","publication_year":2025,"publication_date":"2025-06-02","ids":{"openalex":"https://openalex.org/W4410949714","doi":"https://doi.org/10.1109/tac.2025.3575565"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2025.3575565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3575565","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Transactions on Automatic Control","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mediatum.ub.tum.de/1839813","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023397248","display_name":"Armin Lederer","orcid":"https://orcid.org/0000-0001-6263-5608"},"institutions":[{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]},{"id":"https://openalex.org/I4210090941","display_name":"Institute for Biomedical Engineering","ror":"https://ror.org/00baskk38","country_code":"CH","type":"facility","lineage":["https://openalex.org/I202697423","https://openalex.org/I2799323385","https://openalex.org/I35440088","https://openalex.org/I4210090941"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Armin Lederer","raw_affiliation_strings":["Learning and Adaptive Systems Group, Institute for Machine Learning, Department of Computer Science, ETH Zurich, Zurich, Switzerland","Learning and Adaptive Systems Group, Institute for Machine Learning, Department of Computer Science, ETH Zurich, Switzerland"],"raw_orcid":"https://orcid.org/0000-0001-6263-5608","affiliations":[{"raw_affiliation_string":"Learning and Adaptive Systems Group, Institute for Machine Learning, Department of Computer Science, ETH Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I4210090941"]},{"raw_affiliation_string":"Learning and Adaptive Systems Group, Institute for Machine Learning, Department of Computer Science, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051837539","display_name":"Erfaun Noorani","orcid":"https://orcid.org/0000-0002-5171-122X"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erfaun Noorani","raw_affiliation_strings":["Department of Electrical and Computer Engineering and the Institute for Systems Research (ISR), University of Maryland, College Park, MD, USA","Department of Electrical and Computer Engineering and the Institute for Systems Research (ISR), the University of Maryland, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-5171-122X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Institute for Systems Research (ISR), University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Institute for Systems Research (ISR), the University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044395526","display_name":"John S. Baras","orcid":"https://orcid.org/0000-0002-4955-8561"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John S. Baras","raw_affiliation_strings":["Department of Electrical and Computer Engineering and the Institute for Systems Research (ISR), University of Maryland, College Park, MD, USA","Department of Electrical and Computer Engineering and the Institute for Systems Research (ISR), the University of Maryland, College Park, MD, USA"],"raw_orcid":"https://orcid.org/0000-0002-4955-8561","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Institute for Systems Research (ISR), University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering and the Institute for Systems Research (ISR), the University of Maryland, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024376647","display_name":"Sandra Hirche","orcid":"https://orcid.org/0000-0001-7819-5926"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sandra Hirche","raw_affiliation_strings":["Chair of Information-oriented Control (ITR), School of Computation, Information and Technology, Technical University of Munich, Munich, Germany"],"raw_orcid":"https://orcid.org/0000-0001-7819-5926","affiliations":[{"raw_affiliation_string":"Chair of Information-oriented Control (ITR), School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023397248"],"corresponding_institution_ids":["https://openalex.org/I35440088","https://openalex.org/I4210090941"],"apc_list":null,"apc_paid":null,"fwci":1.166,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.77236058,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"70","issue":"11","first_page":"7414","last_page":"7429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9850999712944031,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11357","display_name":"Risk and Safety Analysis","score":0.9510999917984009,"subfield":{"id":"https://openalex.org/subfields/1804","display_name":"Statistics, Probability and Uncertainty"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7392682433128357},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6912274956703186},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5427215099334717},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4017414450645447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36277279257774353},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.1311483383178711}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7392682433128357},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6912274956703186},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5427215099334717},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4017414450645447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36277279257774353},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1311483383178711}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tac.2025.3575565","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3575565","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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 Transactions on Automatic Control","raw_type":"journal-article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1788988","is_oa":false,"landing_page_url":"https://mediatum.ub.tum.de/1788988","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"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":"article"},{"id":"pmh:oai:mediatum.ub.tum.de:node/1839813","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1839813","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:mediatum.ub.tum.de:node/1839813","is_oa":true,"landing_page_url":"https://mediatum.ub.tum.de/1839813","pdf_url":null,"source":{"id":"https://openalex.org/S4377196330","display_name":"mediaTUM  (Technical University of Munich)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I62916508","host_organization_name":"Technical University of Munich","host_organization_lineage":["https://openalex.org/I62916508"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7133279961","display_name":null,"funder_award_id":"N00014-17-1-2622","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8124193759","display_name":null,"funder_award_id":"51NF40 225155","funder_id":"https://openalex.org/F8269005443","funder_display_name":"NCCR Catalysis"}],"funders":[{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"},{"id":"https://openalex.org/F8269005443","display_name":"NCCR Catalysis","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109"],"abstract_inverted_index":{"Humans":[0],"have":[1,22,84],"the":[2,32,50,69,121,150,156,169],"ability":[3],"to":[4],"deviate":[5],"from":[6,138],"their":[7],"natural":[8],"behavior":[9],"when":[10],"necessary,":[11],"which":[12,119],"is":[13,110,163,173],"a":[14,86,101,113,128],"cognitive":[15],"process":[16],"called":[17],"response":[18,90],"inhibition.":[19],"Similar":[20],"approaches":[21,46],"independently":[23],"received":[24],"increasing":[25],"attention":[26],"in":[27,175],"recent":[28],"years":[29],"for":[30,105,116,130,145],"ensuring":[31],"safety":[33,43,152],"of":[34,52,59,71,74,123,168],"control.":[35,107],"Realized":[36],"using":[37,135,155],"control":[38,61,76,162,171],"barrier":[39],"functions":[40,134],"or":[41],"predictive":[42],"filters,":[44],"these":[45,72,132],"can":[47],"effectively":[48,164],"ensure":[49],"satisfaction":[51,122],"state":[53,124],"constraints":[54],"through":[55,65],"an":[56],"online":[57,154],"adaptation":[58],"nominal":[60],"laws,":[62],"e.g.,":[63],"obtained":[64],"reinforcement":[66,139],"learning.":[67],"While":[68],"focus":[70],"realizations":[73],"inhibitory":[75,106,161],"has":[77],"been":[78],"on":[79,112],"risk-neutral":[80],"formulations,":[81],"human":[82],"studies":[83],"shown":[85],"tight":[87],"link":[88],"between":[89],"inhibition":[91],"and":[92,141],"risk":[93],"attitude.":[94],"Inspired":[95],"by":[96],"this":[97],"insight,":[98],"we":[99],"propose":[100,127],"flexible,":[102],"risk-sensitive":[103,160],"method":[104,109,129],"Our":[108],"based":[111],"risk-aware":[114],"condition":[115],"value":[117,133,158],"functions,":[118],"guarantees":[120],"constraints.":[125],"We":[126],"learning":[131,140],"common":[136],"techniques":[137],"derive":[142],"sufficient":[143],"conditions":[144,153],"its":[146],"success.":[147],"By":[148],"enforcing":[149],"derived":[151],"learned":[157],"function,":[159],"achieved.":[165],"The":[166],"effectiveness":[167],"developed":[170],"scheme":[172],"demonstrated":[174],"simulations.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}