{"id":"https://openalex.org/W7136717072","doi":"https://doi.org/10.1109/itsc60802.2025.11423690","title":"Distributional Soft Actor-Critic with Diffusion Policy","display_name":"Distributional Soft Actor-Critic with Diffusion Policy","publication_year":2025,"publication_date":"2025-11-18","ids":{"openalex":"https://openalex.org/W7136717072","doi":"https://doi.org/10.1109/itsc60802.2025.11423690"},"language":null,"primary_location":{"id":"doi:10.1109/itsc60802.2025.11423690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","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/A5100392648","display_name":"Tong Liu","orcid":"https://orcid.org/0000-0002-4563-167X"},"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":true,"raw_author_name":"Tong Liu","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869516","display_name":"Yinuo Wang","orcid":"https://orcid.org/0009-0006-8117-4425"},"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":"Yinuo Wang","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129415722","display_name":"Xujie Song","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":"Xujie Song","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129600556","display_name":"Wenjun Zou","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":"Wenjun Zou","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026361465","display_name":"Liangfa Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangfa Chen","raw_affiliation_strings":["School of Mechanical Engineering, University of Science and Technology Beijing,Beijing,China,100083"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, University of Science and Technology Beijing,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129415765","display_name":"Likun Wang","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":"Likun Wang","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129618037","display_name":"Bin Shuai","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":"Bin Shuai","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067909017","display_name":"Jingliang Duan","orcid":"https://orcid.org/0000-0002-3697-1576"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingliang Duan","raw_affiliation_strings":["School of Mechanical Engineering, University of Science and Technology Beijing,Beijing,China,100083"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, University of Science and Technology Beijing,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040156274","display_name":"Changliu Liu","orcid":"https://orcid.org/0000-0002-3767-5517"},"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":"Shengbo Eben Li","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100392648"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82846909,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3038","last_page":"3045"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.5601000189781189,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.5601000189781189,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12137","display_name":"Economic theories and models","score":0.09049999713897705,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11151","display_name":"Advanced Topology and Set Theory","score":0.011800000444054604,"subfield":{"id":"https://openalex.org/subfields/2608","display_name":"Geometry and Topology"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4000999927520752},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.29330000281333923},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.2872999906539917},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.27730000019073486},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.26089999079704285}],"concepts":[{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4000999927520752},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.388700008392334},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.37229999899864197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.320499986410141},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3025999963283539},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.29330000281333923},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2442999929189682}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc60802.2025.11423690","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc60802.2025.11423690","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2973229164","https://openalex.org/W3015082424","https://openalex.org/W3136265589","https://openalex.org/W4366158867","https://openalex.org/W4388878609","https://openalex.org/W4406983280","https://openalex.org/W4415797600"],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,54,138],"has":[2],"been":[3],"proven":[4],"to":[5,24,44,65,89,193],"be":[6],"highly":[7],"effective":[8],"in":[9,39,72,172],"handling":[10],"complex":[11],"control":[12,175],"tasks.":[13],"Traditional":[14],"methods":[15],"typically":[16],"use":[17],"unimodal":[18,32],"distributions,":[19,23],"such":[20],"as":[21],"Gaussian":[22],"model":[25],"the":[26,67,90,111,144,148,158,209,217],"output":[27],"of":[28,69,113,122,143,180,188,199,212],"value":[29,40,73,100,105,145],"distributions.":[30],"However,":[31],"distribution":[33,101,112,211],"often":[34],"and":[35,75,99,147,183,216],"easily":[36],"causes":[37],"bias":[38,71,182],"function":[41],"estimation,":[42],"leading":[43],"poor":[45],"algorithm":[46,55,139,160],"performance.":[47],"This":[48],"paper":[49],"proposes":[50],"a":[51,120,129,135],"distributional":[52,82,136],"reinforcement":[53,137],"called":[56],"DSAC-D":[57,205],"(Distributed":[58],"Soft":[59],"Actor":[60],"Critic":[61],"with":[62,140,177],"Diffusion":[63],"Policy)":[64],"address":[66],"challenges":[68],"estimating":[70],"functions":[74],"obtaining":[76],"multimodal":[77,81,164,210,223],"policy":[78,83,92,97,149,219],"representations.":[79],"A":[80,103],"iteration":[84],"framework":[85],"that":[86,107,157,204],"can":[87,108,206,221],"converge":[88],"optimal":[91],"was":[93,116,151],"established":[94],"by":[95,118],"introducing":[96],"entropy":[98],"function.":[102],"diffusion":[104,130,142,218],"network":[106,146,150,220],"accurately":[109,207],"characterize":[110,208,222],"multi":[114],"peaks":[115],"constructed":[117],"generating":[119],"set":[121],"reward":[123],"samples":[124],"through":[125],"reverse":[126],"sampling":[127],"using":[128],"model.":[131],"Based":[132],"on":[133],"this,":[134],"dual":[141],"derived.":[152],"MuJoCo":[153],"testing":[154,202],"tasks":[155],"demonstrate":[156],"proposed":[159],"not":[161],"only":[162],"learns":[163],"policy,":[165],"but":[166],"also":[167],"achieves":[168],"state-of-the-art":[169],"(SOTA)":[170],"performance":[171],"all":[173],"9":[174],"tasks,":[176],"significant":[178],"suppression":[179],"estimation":[181],"total":[184],"average":[185],"return":[186],"improvement":[187],"over":[189],"10":[190],"%":[191],"compared":[192],"existing":[194],"mainstream":[195],"algorithms.":[196],"The":[197],"results":[198],"real":[200],"vehicle":[201],"show":[203],"different":[213],"driving":[214],"styles,":[215],"trajectories.":[224]},"counts_by_year":[],"updated_date":"2026-03-18T06:27:02.140700","created_date":"2026-03-17T00:00:00"}
