{"id":"https://openalex.org/W4390871490","doi":"https://doi.org/10.1109/tro.2024.3354176","title":"Safe Reinforcement Learning in Uncertain Contexts","display_name":"Safe Reinforcement Learning in Uncertain Contexts","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4390871490","doi":"https://doi.org/10.1109/tro.2024.3354176"},"language":"en","primary_location":{"id":"doi:10.1109/tro.2024.3354176","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/tro.2024.3354176","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://dx.doi.org/10.1109/tro.2024.3354176","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029621528","display_name":"Dominik Baumann","orcid":"https://orcid.org/0000-0001-7340-2180"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Dominik Baumann","raw_affiliation_strings":["Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083090794","display_name":"Thomas B. Sch\u00f6n","orcid":"https://orcid.org/0000-0001-5183-234X"},"institutions":[{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Thomas B. Sch\u00f6n","raw_affiliation_strings":["Department of Information Technology, Uppsala University, Uppsala, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Uppsala University, Uppsala, Sweden","institution_ids":["https://openalex.org/I123387679"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029621528"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":{"value":712,"currency":"EUR","value_usd":767},"fwci":0.3454,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60603409,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"40","issue":null,"first_page":"1828","last_page":"1841"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9846000075340271,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9846000075340271,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.978600025177002,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9731000065803528,"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/computer-science","display_name":"Computer science","score":0.6151391267776489},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.598894476890564},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5615515112876892},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5509870052337646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5456287860870361},{"id":"https://openalex.org/keywords/frequentist-inference","display_name":"Frequentist inference","score":0.5188890099525452},{"id":"https://openalex.org/keywords/asset","display_name":"Asset (computer security)","score":0.43655237555503845},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.17724579572677612},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.1522432267665863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6151391267776489},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.598894476890564},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5615515112876892},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5509870052337646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5456287860870361},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.5188890099525452},{"id":"https://openalex.org/C76178495","wikidata":"https://www.wikidata.org/wiki/Q4808784","display_name":"Asset (computer security)","level":2,"score":0.43655237555503845},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.17724579572677612},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.1522432267665863},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tro.2024.3354176","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/tro.2024.3354176","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/126978","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/e1254fe9-566b-4e31-9643-26b4445cbc9f","pdf_url":null,"source":{"id":"https://openalex.org/S4306401662","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"}],"best_oa_location":{"id":"doi:10.1109/tro.2024.3354176","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/tro.2024.3354176","pdf_url":null,"source":{"id":"https://openalex.org/S144620930","display_name":"IEEE Transactions on Robotics","issn_l":"1552-3098","issn":["1552-3098","1941-0468"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315072","display_name":"Mitsubishi Electric Research Laboratories","ror":null},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1970781863","https://openalex.org/W1976985690","https://openalex.org/W2000992741","https://openalex.org/W2019820755","https://openalex.org/W2065313971","https://openalex.org/W2067713319","https://openalex.org/W2112796928","https://openalex.org/W2138859735","https://openalex.org/W2143552356","https://openalex.org/W2146641075","https://openalex.org/W2157801062","https://openalex.org/W2168022998","https://openalex.org/W2194775991","https://openalex.org/W2230652337","https://openalex.org/W2890100993","https://openalex.org/W2905371339","https://openalex.org/W2950476412","https://openalex.org/W3004574756","https://openalex.org/W3023211159","https://openalex.org/W3105376847","https://openalex.org/W3153900045","https://openalex.org/W3157949100","https://openalex.org/W3175352502","https://openalex.org/W3185679378","https://openalex.org/W3195968524","https://openalex.org/W3200082106","https://openalex.org/W4206069766","https://openalex.org/W4211049957","https://openalex.org/W4297629896","https://openalex.org/W6676817345","https://openalex.org/W6678421882","https://openalex.org/W6688325169","https://openalex.org/W6726651112","https://openalex.org/W6736246758","https://openalex.org/W6746752554","https://openalex.org/W6767220907","https://openalex.org/W6773055369","https://openalex.org/W6776500716","https://openalex.org/W6779828752","https://openalex.org/W6785503375","https://openalex.org/W6790756692","https://openalex.org/W6790823767","https://openalex.org/W6845955164"],"related_works":["https://openalex.org/W3124023584","https://openalex.org/W1506744765","https://openalex.org/W193226913","https://openalex.org/W2168076595","https://openalex.org/W2290754432","https://openalex.org/W1559405175","https://openalex.org/W2116258251","https://openalex.org/W2742348189","https://openalex.org/W4225555917","https://openalex.org/W2157736211"],"abstract_inverted_index":{"When":[0],"deploying":[1],"machine":[2],"learning":[3,17,94],"algorithms":[4],"in":[5,27],"the":[6,67,100,117,144],"real":[7],"world,":[8],"guaranteeing":[9],"safety":[10],"is":[11],"an":[12,125],"essential":[13],"asset.":[14],"Existing":[15],"safe":[16,93],"approaches":[18],"typically":[19],"consider":[20],"continuous":[21],"variables,":[22],"i.e.,":[23],"regression":[24],"tasks.":[25],"However,":[26],"practice,":[28],"robotic":[29],"systems":[30],"are":[31],"also":[32],"subject":[33],"to":[34,41,77,115],"discrete,":[35],"external":[36],"environmental":[37],"changes,":[38],"e.g.,":[39],"having":[40],"carry":[42],"objects":[43],"of":[44,146,156],"certain":[45],"weights":[46,158],"or":[47,52],"operating":[48],"on":[49,149],"frozen,":[50],"wet,":[51],"dry":[53],"surfaces.":[54],"Such":[55],"influences":[56],"can":[57,91,138],"be":[58,78],"modeled":[59],"as":[60,161],"discrete":[61],"<italic":[62],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[63],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">context</i>":[64],"variables.":[65,102],"In":[66,80],"existing":[68],"literature,":[69],"such":[70],"contexts":[71,129],"are,":[72],"if":[73],"considered,":[74],"mostly":[75],"assumed":[76],"known.":[79],"this":[81,85],"work,":[82],"we":[83,90,96,106,123,137],"drop":[84],"assumption":[86],"and":[87,142],"show":[88],"how":[89],"perform":[92],"when":[95],"cannot":[97],"directly":[98],"measure":[99],"context":[101,119],"To":[103],"achieve":[104],"this,":[105],"derive":[107],"frequentist":[108],"guarantees":[109,141],"for":[110,127],"multiclass":[111],"classification,":[112],"allowing":[113],"us":[114],"estimate":[116],"current":[118],"from":[120],"measurements.":[121],"Furthermore,":[122],"propose":[124],"approach":[126],"identifying":[128],"through":[130],"experiments.":[131],"We":[132],"discuss":[133],"under":[134],"which":[135],"conditions":[136],"retain":[139],"theoretical":[140],"demonstrate":[143],"applicability":[145],"our":[147],"algorithm":[148],"a":[150],"Furuta":[151],"pendulum":[152],"with":[153],"camera":[154],"measurements":[155],"different":[157],"that":[159],"serve":[160],"contexts.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}