{"id":"https://openalex.org/W4413917936","doi":"https://doi.org/10.1109/icra55743.2025.11127742","title":"Uncertainty-Aware Deep Reinforcement Learning with Calibrated Quantile Regression and Evidential Learning","display_name":"Uncertainty-Aware Deep Reinforcement Learning with Calibrated Quantile Regression and Evidential Learning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413917936","doi":"https://doi.org/10.1109/icra55743.2025.11127742"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5090452169","display_name":"Alex C. Stutts","orcid":"https://orcid.org/0000-0002-4630-5171"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I4210098396","display_name":"Indo-American Center","ror":"https://ror.org/00yw8fx90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098396"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alex C. Stutts","raw_affiliation_strings":["University of Illinois Chicago (UIC)"],"affiliations":[{"raw_affiliation_string":"University of Illinois Chicago (UIC)","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210098396","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021402401","display_name":"Danilo Erricolo","orcid":"https://orcid.org/0000-0001-6352-9567"},"institutions":[{"id":"https://openalex.org/I4210098396","display_name":"Indo-American Center","ror":"https://ror.org/00yw8fx90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098396"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danilo Erricolo","raw_affiliation_strings":["University of Illinois Chicago (UIC)"],"affiliations":[{"raw_affiliation_string":"University of Illinois Chicago (UIC)","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210098396","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062751346","display_name":"Theja Tulabandhula","orcid":"https://orcid.org/0000-0001-9111-7519"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210098396","display_name":"Indo-American Center","ror":"https://ror.org/00yw8fx90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098396"]},{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Theja Tulabandhula","raw_affiliation_strings":["University of Illinois Chicago (UIC)"],"affiliations":[{"raw_affiliation_string":"University of Illinois Chicago (UIC)","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210098396","https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091132933","display_name":"Mohit Mittal","orcid":"https://orcid.org/0000-0003-0878-4615"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Mittal","raw_affiliation_strings":["Meta Reality Lab (MRL)"],"affiliations":[{"raw_affiliation_string":"Meta Reality Lab (MRL)","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028132107","display_name":"Amit Ranjan Trivedi","orcid":"https://orcid.org/0000-0001-5436-7922"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]},{"id":"https://openalex.org/I4210098396","display_name":"Indo-American Center","ror":"https://ror.org/00yw8fx90","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210098396"]},{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amit Ranjan Trivedi","raw_affiliation_strings":["University of Illinois Chicago (UIC)"],"affiliations":[{"raw_affiliation_string":"University of Illinois Chicago (UIC)","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210098396","https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5090452169"],"corresponding_institution_ids":["https://openalex.org/I157725225","https://openalex.org/I39422238","https://openalex.org/I4210098396"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13481266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9651","last_page":"9657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7800999879837036,"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":0.7800999879837036,"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":0.6895999908447266,"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/T10320","display_name":"Neural Networks and Applications","score":0.6310999989509583,"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/quantile-regression","display_name":"Quantile regression","score":0.701193630695343},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6977816820144653},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6780363917350769},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6592453718185425},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6127168536186218},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.4781592786312103},{"id":"https://openalex.org/keywords/quantile","display_name":"Quantile","score":0.4583401679992676},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22929856181144714},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15279358625411987}],"concepts":[{"id":"https://openalex.org/C63817138","wikidata":"https://www.wikidata.org/wiki/Q3455889","display_name":"Quantile regression","level":2,"score":0.701193630695343},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6977816820144653},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6780363917350769},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6592453718185425},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6127168536186218},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.4781592786312103},{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.4583401679992676},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22929856181144714},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15279358625411987}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127742","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127742","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1553101044","https://openalex.org/W2046033161","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2765302304","https://openalex.org/W2953511201","https://openalex.org/W3102100346","https://openalex.org/W3122928565","https://openalex.org/W4212863985","https://openalex.org/W4213251304","https://openalex.org/W4292641317","https://openalex.org/W4385067439","https://openalex.org/W4386285856","https://openalex.org/W4389667277","https://openalex.org/W4392904493","https://openalex.org/W4394593092","https://openalex.org/W4399929809","https://openalex.org/W4401417359"],"related_works":["https://openalex.org/W4206618949","https://openalex.org/W2526321210","https://openalex.org/W3205863630","https://openalex.org/W4318833145","https://openalex.org/W2364275385","https://openalex.org/W4388704167","https://openalex.org/W2007977664","https://openalex.org/W4376874882","https://openalex.org/W2224749288","https://openalex.org/W4252013513"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,132,167],"novel":[3],"statistical":[4,122],"approach":[5,113],"to":[6,93,103,144,156],"incorporate":[7],"uncertainty":[8,73,100],"awareness":[9],"in":[10,28,39,59,74,119,149],"model-free":[11],"distributional":[12],"deep":[13,80],"reinforcement":[14],"learning":[15,22,41,82,152],"for":[16,169],"mission":[17],"and":[18,43,71,121,124,151,163],"safety-critical":[19],"robotics.":[20],"Deep":[21],"predictions":[23],"are":[24],"influenced":[25],"by":[26],"uncertainties":[27,38,159],"the":[29,40,88,111],"data,":[30],"termed":[31],"as":[32,35,37,47,54,101,166],"aleatoric":[33,70],"uncertainties,":[34],"well":[36],"process":[42],"model":[44],"structure,":[45],"known":[46],"epistemic":[48,72],"uncertainties.":[49],"The":[50],"proposed":[51,112],"algorithm,":[52],"called":[53],"Calibrated":[55],"Evidential":[56],"Quantile":[57],"Regression":[58],"Deep-Q":[60],"Networks":[61],"(CEQR-DQN),":[62],"addresses":[63],"key":[64],"challenges":[65],"associated":[66],"with":[67,83],"separately":[68],"estimating":[69],"stochastic":[75],"robotic":[76,172],"environments.":[77],"It":[78],"combines":[79],"evidential":[81],"quantile":[84],"calibration":[85],"based":[86,106],"on":[87,107,131],"principles":[89],"of":[90,98,116,126,134],"conformal":[91],"inference":[92],"provide":[94],"explicit,":[95],"sample-free":[96],"computations":[97],"global":[99],"opposed":[102],"local":[104],"estimates":[105],"simple":[108],"variance.":[109],"Thereby,":[110],"overcomes":[114],"limitations":[115],"traditional":[117],"methods":[118],"computational":[120],"efficiency":[123],"handling":[125],"out-of-distribution":[127],"(OOD)":[128],"observations.":[129],"Tested":[130],"suite":[133],"representative":[135],"miniaturized":[136],"Atari":[137],"games":[138],"(i.e.,":[139],"MinAtar),":[140],"CEQR-DQN":[141],"is":[142],"shown":[143],"surpass":[145],"similar":[146],"existing":[147],"frameworks":[148],"scores":[150],"speed.":[153],"Its":[154],"ability":[155],"rigorously":[157],"evaluate":[158],"improves":[160],"exploration":[161],"strategies":[162],"can":[164],"serve":[165],"blueprint":[168],"other":[170],"uncertainty-aware":[171],"algorithms.":[173]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}