{"id":"https://openalex.org/W2997118265","doi":"https://doi.org/10.5220/0008949905220529","title":"Uncertainty-based Out-of-Distribution Classification in Deep Reinforcement Learning","display_name":"Uncertainty-based Out-of-Distribution Classification in Deep Reinforcement Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W2997118265","doi":"https://doi.org/10.5220/0008949905220529","mag":"2997118265"},"language":"en","primary_location":{"id":"doi:10.5220/0008949905220529","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0008949905220529","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0008949905220529","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Andreas Sedlmeier","orcid":null},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Andreas Sedlmeier","raw_affiliation_strings":["LMU Munich, Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Thomas Gabor","orcid":null},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas Gabor","raw_affiliation_strings":["LMU Munich, Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Thomy Phan","orcid":null},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomy Phan","raw_affiliation_strings":["LMU Munich, Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lenz Belzner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lenz Belzner","raw_affiliation_strings":["MaibornWolff, Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"MaibornWolff, Munich, Germany, --- Select a Country ---","institution_ids":[]}]},{"author_position":"last","author":{"id":null,"display_name":"Claudia Linnhoff-Popien","orcid":null},"institutions":[{"id":"https://openalex.org/I3018771216","display_name":"LMU Klinikum","ror":"https://ror.org/02jet3w32","country_code":"DE","type":"healthcare","lineage":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Claudia Linnhoff-Popien","raw_affiliation_strings":["LMU Munich, Munich, Germany, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3018771216","https://openalex.org/I8204097"],"apc_list":null,"apc_paid":null,"fwci":0.8228,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.78189829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"522","last_page":"529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983999729156494,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983999729156494,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.994700014591217,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9922000169754028,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5952000021934509},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5396999716758728},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.508899986743927},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4754999876022339},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4456000030040741},{"id":"https://openalex.org/keywords/uncertainty-quantification","display_name":"Uncertainty quantification","score":0.4318999946117401},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4074000120162964}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7329000234603882},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6391000151634216},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6317999958992004},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5952000021934509},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5396999716758728},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.3671000003814697},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.3601999878883362},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2687000036239624}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0008949905220529","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0008949905220529","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.00496","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.00496","pdf_url":"https://arxiv.org/pdf/2001.00496","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"doi:10.5220/0008949905220529","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0008949905220529","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Agents and Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Robustness":[0],"to":[1,166],"out-of-distribution":[2],"(OOD)":[3,94],"data":[4,43],"is":[5,70,80],"an":[6,76],"important":[7],"goal":[8],"in":[9,16,44,181],"building":[10],"reliable":[11,150],"machine":[12],"learning":[13,49],"systems.":[14],"Especially":[15],"autonomous":[17],"systems,":[18],"wrong":[19],"predictions":[20],"for":[21,64,82,92,102,129,178],"OOD":[22,66,169,179],"inputs":[23],"can":[24],"cause":[25],"safety":[26],"critical":[27],"situations.":[28,95,170],"As":[29],"a":[30,34,45,56,62,125,131,175],"first":[31,126],"step":[32],"towards":[33,98],"solution,":[35],"we":[36,60],"consider":[37],"the":[38,73,99,137,141,147,159,187,191],"problem":[39,54],"of":[40,140,190],"detecting":[41],"such":[42],"value-based":[46],"deep":[47,182],"reinforcement":[48],"(RL)":[50],"setting.":[51],"Modelling":[52],"this":[53],"as":[55],"one-class":[57],"classification":[58,133,151,180],"problem,":[59],"propose":[61],"framework":[63,148],"uncertainty-based":[65],"classification:":[67],"UBOOD.":[68],"It":[69],"based":[71,135],"on":[72,136],"effect":[74],"that":[75,146],"agent's":[77,192],"epistemic":[78,104,188],"uncertainty":[79,109,138,189],"reduced":[81],"situations":[83],"encountered":[84],"during":[85],"training":[86,142],"(in-distribution),":[87],"and":[88],"thus":[89],"lower":[90],"than":[91],"unencountered":[93],"Being":[96],"agnostic":[97],"approach":[100,177],"used":[101],"estimating":[103],"uncertainty,":[105],"combinations":[106],"with":[107,155,161],"different":[108],"estimation":[110],"methods,":[111],"e.g.":[112],"approximate":[113],"Bayesian":[114],"inference":[115],"methods":[116],"or":[117],"ensembling":[118],"techniques":[119],"are":[120],"possible.":[121],"We":[122],"further":[123],"present":[124],"viable":[127,176],"solution":[128],"calculating":[130],"dynamic":[132],"threshold,":[134],"distribution":[139],"data.":[143],"Evaluation":[144],"shows":[145],"produces":[149],"results":[152],"when":[153],"combined":[154],"ensemble-based":[156],"estimators,":[157],"while":[158],"combination":[160],"concrete":[162],"dropout-based":[163],"estimators":[164],"fails":[165],"reliably":[167],"detect":[168],"In":[171],"summary,":[172],"UBOOD":[173],"presents":[174],"RL":[183],"settings":[184],"by":[185],"leveraging":[186],"value":[193],"function.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-01-10T00:00:00"}