{"id":"https://openalex.org/W7155091578","doi":"https://doi.org/10.1109/access.2026.3685907","title":"Test-Time Confidence Quantification Using Q-Ensembles for Offline RL","display_name":"Test-Time Confidence Quantification Using Q-Ensembles for Offline RL","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7155091578","doi":"https://doi.org/10.1109/access.2026.3685907"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3685907","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3685907","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3685907","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028638932","display_name":"Jason Li","orcid":null},"institutions":[{"id":"https://openalex.org/I283854653","display_name":"Machine Intelligence Research Institute","ror":"https://ror.org/01h4ass90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I283854653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason Li","raw_affiliation_strings":["Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany"],"raw_orcid":"https://orcid.org/0009-0005-3686-3902","affiliations":[{"raw_affiliation_string":"Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany","institution_ids":["https://openalex.org/I283854653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134096113","display_name":"Muhammad Hamza Yousuf","orcid":null},"institutions":[{"id":"https://openalex.org/I283854653","display_name":"Machine Intelligence Research Institute","ror":"https://ror.org/01h4ass90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I283854653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muhammad Hamza Yousuf","raw_affiliation_strings":["Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany","institution_ids":["https://openalex.org/I283854653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134180751","display_name":"Juhyun Seo","orcid":null},"institutions":[{"id":"https://openalex.org/I283854653","display_name":"Machine Intelligence Research Institute","ror":"https://ror.org/01h4ass90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I283854653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Juhyun Seo","raw_affiliation_strings":["Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany"],"raw_orcid":"https://orcid.org/0009-0009-3852-0355","affiliations":[{"raw_affiliation_string":"Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany","institution_ids":["https://openalex.org/I283854653"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134202923","display_name":"Jens Lehmann","orcid":null},"institutions":[{"id":"https://openalex.org/I283854653","display_name":"Machine Intelligence Research Institute","ror":"https://ror.org/01h4ass90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I283854653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jens Lehmann","raw_affiliation_strings":["Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany","institution_ids":["https://openalex.org/I283854653"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134194946","display_name":"Sahar Vahdati","orcid":null},"institutions":[{"id":"https://openalex.org/I283854653","display_name":"Machine Intelligence Research Institute","ror":"https://ror.org/01h4ass90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I283854653"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sahar Vahdati","raw_affiliation_strings":["Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nature-Inspired Machine Intelligence Research Group, Institute for Applied Informatics (InfAI) e.V., Dresden, Germany","institution_ids":["https://openalex.org/I283854653"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54902724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"61867","last_page":"61880"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.5327000021934509,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.5327000021934509,"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/T11032","display_name":"VLSI and Analog Circuit Testing","score":0.2892000079154968,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T13293","display_name":"Engineering and Test Systems","score":0.024900000542402267,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3549000024795532},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.25369998812675476},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.23499999940395355},{"id":"https://openalex.org/keywords/interval","display_name":"Interval (graph theory)","score":0.23149999976158142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7493000030517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5450000166893005},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3059999942779541},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27079999446868896},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.23499999940395355},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.23149999976158142},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22779999673366547},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2190999984741211}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3685907","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3685907","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:abffe78f3a0044ef95db7b677554aaea","is_oa":true,"landing_page_url":"https://doaj.org/article/abffe78f3a0044ef95db7b677554aaea","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 61867-61880 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3685907","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3685907","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7702392339706421,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G3794213272","display_name":"Intelligent Lung Support for Mechanically Ventilated Patients in the Intensive Care Unit","funder_award_id":"101057434","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Confidence":[0],"estimation":[1,152],"plays":[2],"a":[3,35,88,181],"critical":[4],"role":[5],"in":[6,14,30,65,100,164,187,197],"evaluating":[7,82],"the":[8,55,66,119,136,148],"reliability":[9],"of":[10,69,93,139],"trained":[11],"algorithms,":[12],"particularly":[13],"domains":[15,158],"where":[16,42],"incorrect":[17],"decisions":[18],"can":[19,44],"have":[20],"severe":[21],"consequences.":[22],"In":[23],"offline":[24,58,83],"reinforcement":[25],"learning":[26,40],"(RL),":[27],"quantifying":[28],"confidence":[29,43,108,151,191],"an":[31,51,171],"agent\u2019s":[32],"actions":[33],"remains":[34],"significant":[36],"challenge.":[37],"Unlike":[38],"supervised":[39],"models,":[41],"often":[45,79],"be":[46],"assessed":[47],"by":[48],"determining":[49],"whether":[50],"input":[52],"lies":[53],"within":[54],"training":[56],"distribution,":[57],"RL":[59,84,140],"must":[60],"also":[61,179],"account":[62],"for":[63,81,110,121,141,184],"uncertainty":[64,99],"long-term":[67],"outcomes":[68],"state\u2013action":[70],"pairs.":[71],"Consequently,":[72],"standard":[73],"out-of-distribution":[74],"(OOD)":[75],"detection":[76],"methods":[77],"are":[78],"unsuitable":[80],"policies.":[85],"We":[86,113],"propose":[87],"methodology":[89],"that":[90,147],"employs":[91],"ensembles":[92],"critic":[94],"networks":[95],"to":[96,193],"estimate":[97],"epistemic":[98],"action\u2013value":[101],"(<italic":[102],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[103],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Q</i>)":[104],"functions":[105],"and":[106,128,159],"derive":[107],"measures":[109,192],"RL-based":[111,188],"decisions.":[112],"empirically":[114],"validate":[115],"our":[116],"approach":[117],"on":[118,129,135,156],"Dataset":[120],"Deep":[122],"Data-Driven":[123],"Reinforcement":[124],"Learning":[125],"(D4RL)":[126],"benchmarks":[127],"real-world":[130],"eICU":[131],"clinical":[132,167],"data,":[133],"focusing":[134],"high-stakes":[137],"application":[138],"invasive":[142],"mechanical":[143],"ventilation.":[144],"Results":[145],"show":[146],"proposed":[149],"ensemble-based":[150],"achieves":[153],"strong":[154],"discrimination":[155],"benchmark":[157],"retains":[160],"meaningful":[161],"predictive":[162],"value":[163],"more":[165],"complex":[166],"settings.":[168],"Comparison":[169],"with":[170],"autoencoder":[172],"baseline":[173],"shows":[174],"complementary":[175],"strengths.":[176],"This":[177],"framework":[178],"offers":[180],"generalizable":[182],"solution":[183],"improving":[185],"trust":[186],"applications,":[189],"providing":[190],"augment":[194],"decision":[195],"making":[196],"high-stake":[198],"environments.":[199]},"counts_by_year":[],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2026-04-22T00:00:00"}