{"id":"https://openalex.org/W4366308958","doi":"https://doi.org/10.1109/tits.2023.3266885","title":"Identify, Estimate and Bound the Uncertainty of Reinforcement Learning for Autonomous Driving","display_name":"Identify, Estimate and Bound the Uncertainty of Reinforcement Learning for Autonomous Driving","publication_year":2023,"publication_date":"2023-04-18","ids":{"openalex":"https://openalex.org/W4366308958","doi":"https://doi.org/10.1109/tits.2023.3266885"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2023.3266885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2023.3266885","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-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/A5050020266","display_name":"Weitao Zhou","orcid":"https://orcid.org/0000-0002-1266-3843"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weitao Zhou","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1266-3843","affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016651437","display_name":"Zhong Cao","orcid":"https://orcid.org/0000-0002-2243-5705"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong Cao","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-2243-5705","affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013415505","display_name":"Nanshan Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nanshan Deng","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kun Jiang","orcid":"https://orcid.org/0000-0001-7282-172X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Jiang","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7282-172X","affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100735948","display_name":"Diange Yang","orcid":"https://orcid.org/0000-0002-0074-2448"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Diange Yang","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0074-2448","affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.7402,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.83281644,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"24","issue":"8","first_page":"7932","last_page":"7942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9966999888420105,"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/T10524","display_name":"Traffic control and management","score":0.9954000115394592,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.78462153673172},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.7452441453933716},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6302869915962219},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6062029600143433},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5351465940475464},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4974103271961212},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46818554401397705},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.23501238226890564}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.78462153673172},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.7452441453933716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6302869915962219},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6062029600143433},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5351465940475464},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4974103271961212},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46818554401397705},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.23501238226890564},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2023.3266885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2023.3266885","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G1230750079","display_name":null,"funder_award_id":"52102460","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2826808901","display_name":null,"funder_award_id":"Z221100008122011","funder_id":"https://openalex.org/F4320325902","funder_display_name":"Beijing Municipal Science and Technology Commission"},{"id":"https://openalex.org/G7213601597","display_name":null,"funder_award_id":"U22A20104","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320325902","display_name":"Beijing Municipal Science and Technology Commission","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W582134693","https://openalex.org/W1585575029","https://openalex.org/W1931027396","https://openalex.org/W2107338474","https://openalex.org/W2145339207","https://openalex.org/W2151135734","https://openalex.org/W2201581102","https://openalex.org/W2280163991","https://openalex.org/W2525936901","https://openalex.org/W2589869525","https://openalex.org/W2746553466","https://openalex.org/W2749747771","https://openalex.org/W2768542523","https://openalex.org/W2803308811","https://openalex.org/W2904450917","https://openalex.org/W2954742730","https://openalex.org/W2963697717","https://openalex.org/W2991355586","https://openalex.org/W3000193750","https://openalex.org/W3014596384","https://openalex.org/W3033324992","https://openalex.org/W3100147496","https://openalex.org/W3113555494","https://openalex.org/W3118172322","https://openalex.org/W3119981760","https://openalex.org/W3120197634","https://openalex.org/W3134774296","https://openalex.org/W3141426068","https://openalex.org/W3149839747","https://openalex.org/W3201700917","https://openalex.org/W3208617162","https://openalex.org/W4220902452","https://openalex.org/W4244777963","https://openalex.org/W4287073825","https://openalex.org/W4295719664","https://openalex.org/W4297781990","https://openalex.org/W4308068586","https://openalex.org/W4312803983","https://openalex.org/W6617145748","https://openalex.org/W6640490175","https://openalex.org/W6687681856","https://openalex.org/W6695011786","https://openalex.org/W6745935785","https://openalex.org/W6751629939","https://openalex.org/W6771270455","https://openalex.org/W6779265984","https://openalex.org/W6785060721","https://openalex.org/W6791413555","https://openalex.org/W6793364036","https://openalex.org/W6796721416","https://openalex.org/W6799282552"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2961085424","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W4306674287","https://openalex.org/W3111983280","https://openalex.org/W4319083788"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,159],"learning":[2,160],"(DRL)":[3],"has":[4,216],"emerged":[5],"as":[6,143,182],"a":[7,26,54,63,107,138,230,243,247],"promising":[8],"approach":[9],"for":[10,234],"developing":[11],"more":[12,226],"intelligent":[13],"autonomous":[14],"vehicles":[15],"(AVs).":[16],"A":[17],"typical":[18],"DRL":[19,64,98,168,198,210,236,248],"application":[20,237],"on":[21,167,238],"AVs":[22,46],"is":[23,70,101,116,131,141,156,165,212,232],"to":[24,56,71,85,148,203,245],"train":[25],"neural":[27,36],"network-based":[28],"driving":[29,65,180,240],"policy.":[30,66,109,199,249],"However,":[31],"the":[32,75,95,97,119,123,127,144,189,209,220,235],"black-box":[33],"nature":[34],"of":[35,62,106,173,197,222],"networks":[37],"can":[38,192],"result":[39,186],"in":[40],"unpredictable":[41],"decision":[42,151],"failures,":[43],"making":[44],"such":[45],"unreliable.":[47],"To":[48],"this":[49,51],"end,":[50],"work":[52],"proposes":[53],"method":[55,191,231],"identify":[57,193],"and":[58,73,215,241],"protect":[59],"unreliable":[60,195],"decisions":[61,196],"The":[67,110,153,162,185,200],"basic":[68],"idea":[69],"estimate":[72],"constrain":[74],"policy\u2019s":[76],"performance":[77,82,100,145,221],"uncertainty,":[78,96],"which":[79],"quantifies":[80],"potential":[81,150],"drop":[83],"due":[84],"insufficient":[86,114],"training":[87,174,227],"data":[88,115],"or":[89],"network":[90,128],"fitting":[91,129],"errors.":[92],"By":[93],"constraining":[94],"model\u2019s":[99],"always":[102],"greater":[103],"than":[104],"that":[105,188],"baseline":[108,139,205],"uncertainty":[111,124],"caused":[112,125],"by":[113,118,126],"estimated":[117,132],"bootstrapped":[120],"method.":[121],"Then,":[122],"error":[130],"using":[133],"an":[134,177,183],"ensemble":[135],"network.":[136],"Finally,":[137],"policy":[140,206,211],"added":[142],"lower":[146],"bound":[147],"avoid":[149],"failures.":[152],"overall":[154],"framework":[155],"called":[157],"uncertainty-bound":[158],"(UBRL).":[161],"proposed":[163],"UBRL":[164,190,201,223],"evaluated":[166],"policies":[169],"with":[170,225],"different":[171],"amounts":[172],"data,":[175],"taking":[176],"unprotected":[178],"left-turn":[179],"case":[181],"example.":[184],"shows":[187],"potentially":[194],"guarantees":[202],"outperform":[204],"even":[207],"when":[208],"not":[213],"well-trained":[214],"high":[217],"uncertainty.":[218],"Meanwhile,":[219],"improves":[224],"data.":[228],"Such":[229],"valuable":[233],"real-road":[239],"provides":[242],"metric":[244],"evaluate":[246]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}