{"id":"https://openalex.org/W7124303565","doi":"https://doi.org/10.65109/msgn4745","title":"Towards Anomaly Detection in Reinforcement Learning","display_name":"Towards Anomaly Detection in Reinforcement Learning","publication_year":2022,"publication_date":"2022-05-09","ids":{"openalex":"https://openalex.org/W7124303565","doi":"https://doi.org/10.65109/msgn4745"},"language":"en","primary_location":{"id":"doi:10.65109/msgn4745","doi":"https://doi.org/10.65109/msgn4745","is_oa":false,"landing_page_url":"https://doi.org/10.65109/msgn4745","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5153322052","display_name":"Robert M\u00fcller","orcid":null,"observed_orcids":[]},"institutions":[{"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":"Robert M\u00fcller","raw_affiliation_strings":["LMU Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069846773","display_name":"Steffen Illium","orcid":"https://orcid.org/0000-0003-0021-436X","observed_orcids":["https://orcid.org/0000-0003-0021-436X"]},"institutions":[{"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":"Steffen Illium","raw_affiliation_strings":["LMU Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024645861","display_name":"Thomy Phan","orcid":"https://orcid.org/0000-0002-4390-8954","observed_orcids":["https://orcid.org/0000-0002-4390-8954"]},"institutions":[{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087368349","display_name":"Tom Haider","orcid":"https://orcid.org/0000-0001-6786-0361","observed_orcids":["https://orcid.org/0000-0001-6786-0361"]},"institutions":[{"id":"https://openalex.org/I4210127444","display_name":"Fraunhofer Institute for Cognitive Systems","ror":"https://ror.org/02fez3815","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210127444","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tom Haider","raw_affiliation_strings":["Fraunhofer IKS, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IKS, Munich, Germany","institution_ids":["https://openalex.org/I4210127444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064469861","display_name":"Claudia Linnhoff\u2013Popien","orcid":"https://orcid.org/0000-0001-6284-9286","observed_orcids":["https://orcid.org/0000-0001-6284-9286"]},"institutions":[{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LMU Munich, Munich, Germany","institution_ids":["https://openalex.org/I8204097"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2136,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.4995682,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1799","last_page":"1803"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5835000276565552,"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":0.5835000276565552,"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":0.4000999927520752,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.006300000008195639,"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/anomaly-detection","display_name":"anomaly detection","score":0.9779999852180481},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9950000047683716},{"id":"https://openalex.org/keywords/nonstationarity","display_name":"non-stationarity","score":0.699999988079071},{"id":"https://openalex.org/keywords/lifelong-reinforcement-learning","display_name":"lifelong reinforcement learning","score":0.9430000185966492},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.9449999928474426},{"id":"https://openalex.org/keywords/safety-critical-systems","display_name":"safety-critical systems","score":0.7739999890327454},{"id":"https://openalex.org/keywords/sequential-decision-making","display_name":"sequential decision making","score":0.8169999718666077}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.7598000168800354},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7269999980926514},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7052000164985657},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5217000246047974},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4562000036239624},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41909998655319214},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C169087156","wikidata":"https://www.wikidata.org/wiki/Q2131593","display_name":"Framing (construction)","level":2,"score":0.37380000948905945},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.36500000953674316},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.31769999861717224},{"id":"https://openalex.org/C2776157432","wikidata":"https://www.wikidata.org/wiki/Q1375683","display_name":"Normality","level":2,"score":0.2863999903202057},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C12997251","wikidata":"https://www.wikidata.org/wiki/Q567560","display_name":"Anomaly (physics)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.25760000944137573},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C123197309","wikidata":"https://www.wikidata.org/wiki/Q2882343","display_name":"Multi-armed bandit","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.65109/msgn4745","doi":"https://doi.org/10.65109/msgn4745","is_oa":false,"landing_page_url":"https://doi.org/10.65109/msgn4745","pdf_url":null,"source":{"id":"https://openalex.org/S4306417597","display_name":"Adaptive Agents and Multi-Agents Systems","issn_l":"1548-8403","issn":["1548-8403"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"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":"International Joint Conference on Autonomous Agents and Multiagent Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7204599126","https://openalex.org/W6922910102","https://openalex.org/W3199730831","https://openalex.org/W7125258919","https://openalex.org/W3131543739","https://openalex.org/W7124265117","https://openalex.org/W3019983973","https://openalex.org/W7115068861","https://openalex.org/W4416058283","https://openalex.org/W4409601226"],"abstract_inverted_index":{"Identifying":[0],"datapoints":[1],"that":[2,54,102],"substantially":[3],"differ":[4],"from":[5,148],"normality":[6],"is":[7,46,67],"the":[8,39,49,89,96,144,159,180,188],"task":[9],"of":[10,41,52,68,91,98,158,179,187,201],"anomaly":[11,63],"detection":[12],"(AD).":[13],"While":[14],"AD":[15,93,123,166],"has":[16,32,33],"gained":[17],"widespread":[18],"attention":[19],"in":[20,38,71,81,95,124,129,167,185],"rich":[21],"data":[22,78],"domains":[23],"such":[24,131],"as":[25,132],"images,":[26],"videos,":[27],"audio":[28],"and":[29,106,111,135,142,169],"text,":[30],"it":[31,184],"been":[34],"studied":[35],"less":[36],"frequently":[37],"context":[40,97],"reinforcement":[42],"learning":[43],"(RL).":[44],"This":[45],"due":[47],"to":[48,116,126,155],"additional":[50],"layer":[51],"complexity":[53],"RL":[55,66,125,130,134,168],"introduces":[56],"through":[57],"sequential":[58],"decision":[59,194],"making.":[60],"Developing":[61],"suitable":[62],"detectors":[64],"for":[65,162,204],"particular":[69],"importance":[70],"safety-critical":[72],"scenarios":[73,113],"where":[74],"acting":[75],"on":[76,108,165],"anomalous":[77],"could":[79],"result":[80],"hazardous":[82],"situations.":[83],"In":[84],"this":[85],"work,":[86],"we":[87,152,197],"address":[88],"question":[90],"what":[92],"means":[94],"RL.":[99],"We":[100,121,137],"found":[101],"current":[103],"research":[104,164],"trains":[105],"evaluates":[107],"overly":[109],"simplistic":[110],"unrealistic":[112],"which":[114],"reduce":[115],"classic":[117],"pattern":[118],"recognition":[119],"tasks.":[120],"link":[122],"various":[127],"fields":[128,145],"lifelong":[133],"generalization.":[136],"discuss":[138],"their":[139],"similarities,":[140],"differences,":[141],"how":[143],"can":[146],"benefit":[147],"each":[149],"other.":[150],"Moreover,":[151],"identify":[153],"non-stationarity":[154],"be":[156],"one":[157],"key":[160],"drivers":[161],"future":[163,205],"make":[170],"a":[171,175,199],"first":[172],"step":[173],"towards":[174],"more":[176],"formal":[177],"treatment":[178],"problem":[181],"by":[182],"framing":[183],"terms":[186],"recently":[189],"introduced":[190],"block":[191],"contextual":[192],"Markov":[193],"process.":[195],"Finally,":[196],"define":[198],"list":[200],"practical":[202],"desiderata":[203],"problems.":[206]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-01-16T00:00:00"}