{"id":"https://openalex.org/W7128427801","doi":"https://doi.org/10.1109/tits.2026.3657609","title":"Reinforcement Learning for Driving Policy Generalization via Risk-Aware Expert Policy and Conditional Diffusion","display_name":"Reinforcement Learning for Driving Policy Generalization via Risk-Aware Expert Policy and Conditional Diffusion","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128427801","doi":"https://doi.org/10.1109/tits.2026.3657609"},"language":null,"primary_location":{"id":"doi:10.1109/tits.2026.3657609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2026.3657609","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/A5125455757","display_name":"Guofa Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guofa Li","raw_affiliation_strings":["State Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing Changan Automobile Company Ltd., Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-7889-4695","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing Changan Automobile Company Ltd., Chongqing, China","institution_ids":["https://openalex.org/I4210145005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125437082","display_name":"Yingchen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yingchen Wang","raw_affiliation_strings":["College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021600978","display_name":"Delin Ouyang","orcid":"https://orcid.org/0000-0003-3137-6089"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Delin Ouyang","raw_affiliation_strings":["College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0003-3137-6089","affiliations":[{"raw_affiliation_string":"College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125447224","display_name":"Jie Li","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-3718-5593","affiliations":[{"raw_affiliation_string":"College of Mechanical and Vehicle Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061628630","display_name":"Xiangyun Ren","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145005","display_name":"State Key Laboratory of Vehicle NVH and Safety Technology","ror":"https://ror.org/04e6h1p91","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145005"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyun Ren","raw_affiliation_strings":["State Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing Changan Automobile Company Ltd., Chongqing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing Changan Automobile Company Ltd., Chongqing, China","institution_ids":["https://openalex.org/I4210145005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12238011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"5","first_page":"6050","last_page":"6062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.4408000111579895,"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":0.4408000111579895,"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":0.35420000553131104,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03700000047683716,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7236999869346619},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6984999775886536},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5320000052452087},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.505299985408783},{"id":"https://openalex.org/keywords/data-driven","display_name":"Data-driven","score":0.5006999969482422},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.48510000109672546},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4616999924182892},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4458000063896179},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.3944000005722046}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7236999869346619},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6984999775886536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6385999917984009},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5320000052452087},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.5006999969482422},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.48510000109672546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4691999852657318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4650999903678894},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4616999924182892},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4458000063896179},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3944000005722046},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.34290000796318054},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.26750001311302185},{"id":"https://openalex.org/C47796450","wikidata":"https://www.wikidata.org/wiki/Q508378","display_name":"Intelligent transportation system","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.2581000030040741},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2026.3657609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2026.3657609","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":[{"score":0.41457703709602356,"display_name":"No poverty","id":"https://metadata.un.org/sdg/1"}],"awards":[{"id":"https://openalex.org/G2485756858","display_name":null,"funder_award_id":"IVSTSKL-202425","funder_id":"https://openalex.org/F4320330424","funder_display_name":"Key Laboratory of Intelligent Multimedia Technology"}],"funders":[{"id":"https://openalex.org/F4320330424","display_name":"Key Laboratory of Intelligent Multimedia Technology","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,44],"real-world":[1],"autonomous":[2],"driving":[3,228],"applications,":[4],"reinforcement":[5],"learning":[6,225],"(RL)":[7],"faces":[8],"several":[9],"persistent":[10],"challenges":[11],"including":[12],"limited":[13],"critical":[14,145],"training":[15,157],"data,":[16,158],"low":[17],"exploration":[18,80],"efficiency,":[19],"and":[20,39,68,89,173,226,247],"poor":[21],"policy":[22,75,127,185,209,224],"generalization.":[23,248],"These":[24],"limitations":[25],"often":[26],"result":[27],"in":[28,33,155,211,243],"slow":[29],"convergence":[30],"or":[31],"stagnation":[32],"local":[34],"optima,":[35],"undermining":[36],"the":[37,85,93,109,137,150,156,184,190,196,200],"safety":[38,246],"generalization":[40,210],"of":[41,96,111,152,245],"intelligent":[42],"vehicles.":[43],"order":[45],"to":[46,78,84,107,125,142,148,208],"address":[47],"these":[48],"issues,":[49],"we":[50,99,159],"propose":[51,100,160],"a":[52,72,101,161],"generation-enhanced":[53],"RL":[54],"framework":[55],"for":[56],"challenging":[57],"decision-making":[58],"scenarios,":[59],"which":[60,180],"comprises":[61],"three":[62],"stages:":[63],"data":[64,66,69],"acquisition,":[65],"utilization,":[67],"generation.":[70],"Firstly,":[71],"risk-aware":[73],"expert":[74],"is":[76,181],"developed":[77],"guide":[79],"on":[81,122,166],"regions":[82],"proximal":[83],"boundary":[86],"between":[87],"safe":[88],"unsafe":[90],"actions":[91],"during":[92,135],"early":[94],"phases":[95],"training.":[97],"Secondly,":[98],"hierarchical":[102],"dynamic":[103],"prioritized":[104],"replay":[105,115,201],"mechanism":[106],"enhance":[108],"utilization":[110],"collected":[112],"experiences.":[113],"The":[114,233],"buffer":[116,202],"dynamically":[117],"ranks":[118],"experience":[119],"samples":[120],"based":[121,165],"their":[123,241],"relevance":[124],"current":[126],"updates.":[128],"By":[129,188],"weighting":[130],"essential":[131],"transitions":[132,154,176],"more":[133],"heavily":[134],"replay,":[136],"agent":[138],"gains":[139],"enhanced":[140],"capability":[141],"learn":[143],"from":[144],"scenarios.":[146,215,232],"Thirdly,":[147],"mitigate":[149],"scarcity":[151],"high-risk":[153,191],"conditional":[162,194],"generation":[163,197],"method":[164,221],"diffusion":[167],"model.":[168],"This":[169],"model":[170,198],"synthesizes":[171],"diverse":[172],"structurally":[174],"relevant":[175],"with":[177],"statistical":[178],"realism,":[179],"concentrated":[182],"near":[183],"decision":[186],"boundary.":[187],"employing":[189],"metric":[192],"as":[193],"input,":[195],"supplements":[199],"by":[203],"covering":[204],"distributional":[205],"gaps,":[206],"leading":[207],"rare":[212],"but":[213],"safety-critical":[214],"Experimental":[216],"results":[217],"demonstrate":[218],"that":[219],"our":[220],"significantly":[222],"accelerates":[223],"improves":[227],"performance":[229],"under":[230],"complex":[231],"learned":[234],"policies":[235],"also":[236],"outperform":[237],"existing":[238],"baselines,":[239],"indicating":[240],"advantages":[242],"terms":[244]},"counts_by_year":[],"updated_date":"2026-05-08T13:12:06.581006","created_date":"2026-02-10T00:00:00"}