{"id":"https://openalex.org/W4391019719","doi":"https://doi.org/10.1109/cdc49753.2023.10383524","title":"Risk-Sensitive Inhibitory Control for Safe Reinforcement Learning","display_name":"Risk-Sensitive Inhibitory Control for Safe Reinforcement Learning","publication_year":2023,"publication_date":"2023-12-13","ids":{"openalex":"https://openalex.org/W4391019719","doi":"https://doi.org/10.1109/cdc49753.2023.10383524"},"language":"en","primary_location":{"id":"doi:10.1109/cdc49753.2023.10383524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE 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/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":true,"raw_author_name":"Armin Lederer","raw_affiliation_strings":["School of Computation, Information and Technology, Technical University of Munich,Chair of Information-oriented Control (ITR),Munich,Germany,80333"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Chair of Information-oriented Control (ITR),Munich,Germany,80333","institution_ids":["https://openalex.org/I62916508"]}]},{"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":["Institute for Systems Research (ISR) at the University of Maryland,Department of Electrical and Computer Engineering,College Park,MD,USA","Department of Electrical and Computer Engineering, Institute for Systems Research (ISR) at the University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Systems Research (ISR) at the University of Maryland,Department of Electrical and Computer Engineering,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute for Systems Research (ISR) at 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":["Institute for Systems Research (ISR) at the University of Maryland,Department of Electrical and Computer Engineering,College Park,MD,USA","Department of Electrical and Computer Engineering, Institute for Systems Research (ISR) at the University of Maryland, College Park, MD, USA"],"affiliations":[{"raw_affiliation_string":"Institute for Systems Research (ISR) at the University of Maryland,Department of Electrical and Computer Engineering,College Park,MD,USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Institute for Systems Research (ISR) at 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":["School of Computation, Information and Technology, Technical University of Munich,Chair of Information-oriented Control (ITR),Munich,Germany,80333"],"affiliations":[{"raw_affiliation_string":"School of Computation, Information and Technology, Technical University of Munich,Chair of Information-oriented Control (ITR),Munich,Germany,80333","institution_ids":["https://openalex.org/I62916508"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023397248"],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":0.4185,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69786223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1040","last_page":"1045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10826","display_name":"Behavioral and Psychological Studies","score":0.9460999965667725,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10826","display_name":"Behavioral and Psychological Studies","score":0.9460999965667725,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9377999901771545,"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/T10142","display_name":"Formal Methods in Verification","score":0.9315999746322632,"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":0.891372799873352},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6275638937950134},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5682201981544495},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5624048709869385},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4534953534603119},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42239853739738464},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.42047062516212463},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.41848224401474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39077186584472656},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3706086277961731},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.23882225155830383}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.891372799873352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6275638937950134},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5682201981544495},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5624048709869385},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4534953534603119},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42239853739738464},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.42047062516212463},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.41848224401474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39077186584472656},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3706086277961731},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23882225155830383},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc49753.2023.10383524","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc49753.2023.10383524","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 62nd IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G4056338224","display_name":null,"funder_award_id":"864686","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"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"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1979172694","https://openalex.org/W2048469131","https://openalex.org/W2127082526","https://openalex.org/W2158782408","https://openalex.org/W2753794385","https://openalex.org/W2770616710","https://openalex.org/W2950402429","https://openalex.org/W2963238274","https://openalex.org/W2963575966","https://openalex.org/W2996196387","https://openalex.org/W3120459386","https://openalex.org/W3121342653","https://openalex.org/W3166231878","https://openalex.org/W3173331501","https://openalex.org/W3186708588","https://openalex.org/W3195968524","https://openalex.org/W4211049957","https://openalex.org/W4214717370","https://openalex.org/W4315488635","https://openalex.org/W6730042731","https://openalex.org/W6747473740","https://openalex.org/W6752963931","https://openalex.org/W6772100842"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"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":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
