{"id":"https://openalex.org/W7143351333","doi":"https://doi.org/10.1109/lra.2026.3678842","title":"Learning Rollout from Sampling: An R1-Style Tokenized Traffic Simulation Model","display_name":"Learning Rollout from Sampling: An R1-Style Tokenized Traffic Simulation Model","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7143351333","doi":"https://doi.org/10.1109/lra.2026.3678842"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3678842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3678842","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2603.24989","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130659548","display_name":"Ziyan Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyan Wang","raw_affiliation_strings":["State Key Laboratory of Intelligent Transportation System, Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, School of Transportation Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-7170-0729","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Transportation System, Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, School of Transportation Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210127216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130967446","display_name":"Peng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Chen","raw_affiliation_strings":["State Key Laboratory of Intelligent Transportation System, Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, School of Transportation Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8076-8989","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Transportation System, Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, School of Transportation Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210127216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130945714","display_name":"Ding Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Li","raw_affiliation_strings":["State Key Laboratory of Intelligent Transportation System, Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, School of Transportation Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-4613-8610","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Transportation System, Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, School of Transportation Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210127216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130755890","display_name":"Chiwei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chiwei Li","raw_affiliation_strings":["State Key Laboratory of Intelligent Transportation System, Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, School of Transportation Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Transportation System, Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, School of Transportation Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210127216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130934249","display_name":"Qichao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qichao Zhang","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9747-391X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065256108","display_name":"Zhongpu Xia","orcid":"https://orcid.org/0009-0003-4251-6849"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongpu Xia","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130925749","display_name":"Guizhen Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127216","display_name":"Ministry of Transport","ror":"https://ror.org/031wq1t38","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210127216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guizhen Yu","raw_affiliation_strings":["State Key Laboratory of Intelligent Transportation System, Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, School of Transportation Science and Engineering, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8374-7422","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Transportation System, Key Laboratory of Autonomous Transportation Technology for Special Vehicles, Ministry of Industry and Information Technology, School of Transportation Science and Engineering, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210127216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.32183457,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"5","first_page":"6336","last_page":"6343"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.37290000915527344,"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"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.37290000915527344,"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"}},{"id":"https://openalex.org/T10698","display_name":"Transportation Planning and Optimization","score":0.16680000722408295,"subfield":{"id":"https://openalex.org/subfields/3313","display_name":"Transportation"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.11819999665021896,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/key","display_name":"Key (lock)","score":0.34779998660087585},{"id":"https://openalex.org/keywords/interoperability","display_name":"Interoperability","score":0.31529998779296875},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.2581999897956848}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5078999996185303},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34779998660087585},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.27070000767707825},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.26899999380111694},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.25850000977516174},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2558000087738037},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2026.3678842","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3678842","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"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 Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2603.24989","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.24989","pdf_url":"https://arxiv.org/pdf/2603.24989","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2603.24989","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2603.24989","pdf_url":"https://arxiv.org/pdf/2603.24989","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G297144773","display_name":null,"funder_award_id":"52272327","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3328537259","display_name":null,"funder_award_id":"62503033","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning":[0],"diverse":[1,159,171],"and":[2,35,100,162,170],"high-fidelity":[3],"traffic":[4,33,81],"simulations":[5],"from":[6],"human":[7],"driving":[8,14],"demonstrations":[9],"is":[10],"crucial":[11],"for":[12,64],"autonomous":[13],"evaluation.":[15],"The":[16],"recent":[17],"next-token":[18],"prediction":[19],"(NTP)":[20],"paradigm,":[21],"widely":[22],"adopted":[23],"in":[24,55,167],"large":[25],"language":[26],"models":[27],"(LLMs),":[28],"has":[29],"been":[30],"applied":[31],"to":[32,90,189],"simulation":[34,82,110],"achieves":[36,185],"iterative":[37],"improvements":[38],"via":[39],"supervised":[40],"fine-tuning":[41],"(SFT).":[42],"However,":[43],"such":[44],"methods":[45],"limit":[46],"active":[47],"exploration":[48,66],"of":[49,105],"potentially":[50],"valuable":[51],"motion":[52,69,96,107,125,136],"tokens,":[53],"particularly":[54],"suboptimal":[56],"regions.":[57],"Entropy":[58],"patterns":[59],"provide":[60],"a":[61,78,146,154],"promising":[62],"perspective":[63],"enabling":[65],"driven":[67],"by":[68,73,145],"token":[70,97],"uncertainty.":[71],"Motivated":[72],"this":[74],"insight,":[75],"we":[76,113],"propose":[77],"novel":[79],"tokenized":[80],"policy,":[83],"R1Sim,":[84],"which":[85],"represents":[86],"an":[87,115],"initial":[88],"attempt":[89],"explore":[91],"reinforcement":[92],"learning":[93],"based":[94],"on":[95,109,122,176],"entropy":[98],"patterns,":[99],"systematically":[101],"analyzes":[102],"the":[103,177],"impact":[104],"different":[106],"tokens":[108,126],"outcomes.":[111],"Specifically,":[112],"introduce":[114],"entropy-guided":[116],"adaptive":[117],"sampling":[118,161],"mechanism":[119],"that":[120,183],"focuses":[121],"previously":[123],"overlooked":[124],"with":[127],"high":[128,131],"uncertainty":[129],"yet":[130],"potential.":[132],"We":[133],"further":[134],"optimize":[135],"behaviors":[137],"using":[138],"Group":[139],"Relative":[140],"Policy":[141],"Optimization":[142],"(GRPO),":[143],"guided":[144],"safety-aware":[147],"reward":[148],"design.":[149],"Overall,":[150],"these":[151],"components":[152],"enable":[153],"balanced":[155],"exploration\u2013exploitation":[156],"trade-off":[157],"through":[158],"high-uncertainty":[160],"group-wise":[163],"comparative":[164],"estimation,":[165],"resulting":[166],"realistic,":[168],"safe,":[169],"multi-agent":[172],"behaviors.":[173],"Extensive":[174],"experiments":[175],"Waymo":[178],"Sim":[179],"Agent":[180],"benchmark":[181],"demonstrate":[182],"R1Sim":[184],"competitive":[186],"performance":[187],"compared":[188],"state-of-the-art":[190],"methods.":[191]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-31T00:00:00"}