{"id":"https://openalex.org/W4315488635","doi":"https://doi.org/10.1109/cdc51059.2022.9992470","title":"Safe Reinforcement Learning via Confidence-Based Filters","display_name":"Safe Reinforcement Learning via Confidence-Based Filters","publication_year":2022,"publication_date":"2022-12-06","ids":{"openalex":"https://openalex.org/W4315488635","doi":"https://doi.org/10.1109/cdc51059.2022.9992470"},"language":"en","primary_location":{"id":"doi:10.1109/cdc51059.2022.9992470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992470","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5038306778","display_name":"Sebastian Curi","orcid":null},"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"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Sebastian Curi","raw_affiliation_strings":["ETH Zurich,LAS Group,Department of Computer Science,Switzerland","Department of Computer Science, LAS Group, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,LAS Group,Department of Computer Science,Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Computer Science, LAS Group, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023397248","display_name":"Armin Lederer","orcid":"https://orcid.org/0000-0001-6263-5608"},"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":"Armin Lederer","raw_affiliation_strings":["Technical University of Munich,Chair of Information-Oriented Control,Department of Electrical and Computer Engineering,Germany","Department of Electrical and Computer Engineering, Chair of Information-Oriented Control, Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Chair of Information-Oriented Control,Department of Electrical and Computer Engineering,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Chair of Information-Oriented Control, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","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":["Technical University of Munich,Chair of Information-Oriented Control,Department of Electrical and Computer Engineering,Germany","Department of Electrical and Computer Engineering, Chair of Information-Oriented Control, Technical University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Chair of Information-Oriented Control,Department of Electrical and Computer Engineering,Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Chair of Information-Oriented Control, Technical University of Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003040843","display_name":"Andreas Krause","orcid":"https://orcid.org/0000-0001-7260-9673"},"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"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Andreas Krause","raw_affiliation_strings":["ETH Zurich,LAS Group,Department of Computer Science,Switzerland","Department of Computer Science, LAS Group, ETH Zurich, Switzerland"],"affiliations":[{"raw_affiliation_string":"ETH Zurich,LAS Group,Department of Computer Science,Switzerland","institution_ids":["https://openalex.org/I35440088"]},{"raw_affiliation_string":"Department of Computer Science, LAS Group, ETH Zurich, Switzerland","institution_ids":["https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5038306778"],"corresponding_institution_ids":["https://openalex.org/I35440088"],"apc_list":null,"apc_paid":null,"fwci":0.3254,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.56723716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"3409","last_page":"3415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9965999722480774,"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"}},"topics":[{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9965999722480774,"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/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.9919000267982483,"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/T10142","display_name":"Formal Methods in Verification","score":0.991100013256073,"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":0.8745319843292236},{"id":"https://openalex.org/keywords/backup","display_name":"Backup","score":0.8493417501449585},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.699893593788147},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6377658843994141},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.49100616574287415},{"id":"https://openalex.org/keywords/hallucinating","display_name":"Hallucinating","score":0.47253158688545227},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4663969874382019},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.4605253338813782},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44186705350875854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34452420473098755},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1661665439605713},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1233997642993927},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09592035412788391}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8745319843292236},{"id":"https://openalex.org/C2780945871","wikidata":"https://www.wikidata.org/wiki/Q194274","display_name":"Backup","level":2,"score":0.8493417501449585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.699893593788147},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6377658843994141},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.49100616574287415},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.47253158688545227},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4663969874382019},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.4605253338813782},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44186705350875854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34452420473098755},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1661665439605713},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1233997642993927},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09592035412788391},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc51059.2022.9992470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc51059.2022.9992470","pdf_url":null,"source":{"id":"https://openalex.org/S4363607710","display_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 61st Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320334678","display_name":"European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1825869920","https://openalex.org/W1845972764","https://openalex.org/W1995713768","https://openalex.org/W2001951765","https://openalex.org/W2118200824","https://openalex.org/W2158782408","https://openalex.org/W2557055507","https://openalex.org/W2753794385","https://openalex.org/W2770616710","https://openalex.org/W2892521964","https://openalex.org/W2963525569","https://openalex.org/W2963683522","https://openalex.org/W2973076431","https://openalex.org/W2996196387","https://openalex.org/W3047267560","https://openalex.org/W3120459386","https://openalex.org/W3121342653","https://openalex.org/W3135206495","https://openalex.org/W3186708588","https://openalex.org/W3195968524","https://openalex.org/W4206497039","https://openalex.org/W4214717370","https://openalex.org/W4287756978","https://openalex.org/W4297824337","https://openalex.org/W6684921986","https://openalex.org/W6735677848","https://openalex.org/W6737893269","https://openalex.org/W6747473740","https://openalex.org/W6770009701","https://openalex.org/W6772100842","https://openalex.org/W6774406872","https://openalex.org/W6779911313","https://openalex.org/W6790964287","https://openalex.org/W6791798161"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W4225571923","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W3212257828","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915"],"abstract_inverted_index":{"Ensuring":[0],"safety":[1,17,25,56,117],"is":[2,42,80,92],"a":[3,19,45,59,76,100],"crucial":[4],"challenge":[5],"when":[6],"deploying":[7],"reinforcement":[8],"learning":[9],"(RL)":[10],"to":[11,58,74],"real-world":[12],"systems.":[13],"We":[14,114],"develop":[15],"confidence-based":[16],"filters,":[18],"control-theoretic":[20],"approach":[21,41],"for":[22,27,82],"certifying":[23],"state":[24,48],"constraints":[26,49],"nominal":[28,90],"policies":[29],"learnt":[30],"via":[31],"standard":[32,60],"RL":[33,61],"techniques,":[34],"based":[35,43],"on":[36,44],"probabilistic":[37],"dynamics":[38],"models.":[39],"Our":[40],"reformulation":[46],"of":[47,52,67,124],"in":[50],"terms":[51],"cost":[53],"functions,":[54],"reducing":[55],"verification":[57],"task.":[62],"By":[63],"exploiting":[64],"the":[65,83,103,122],"concept":[66],"hallucinating":[68],"inputs,":[69],"we":[70],"extend":[71],"this":[72],"formulation":[73],"determine":[75],"\"backup\"":[77],"policy":[78,91],"which":[79],"safe":[81,108],"unknown":[84],"system":[85],"with":[86],"high":[87],"probability.":[88],"The":[89],"minimally":[93],"adjusted":[94],"at":[95],"every":[96],"time":[97],"step":[98],"during":[99],"roll-out":[101],"towards":[102],"backup":[104],"policy,":[105],"such":[106],"that":[107],"recovery":[109],"can":[110],"be":[111],"guaranteed":[112],"afterwards.":[113],"provide":[115],"formal":[116],"guarantees,":[118],"and":[119],"empirically":[120],"demonstrate":[121],"effectiveness":[123],"our":[125],"approach.":[126]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}