{"id":"https://openalex.org/W4388327604","doi":"https://doi.org/10.48550/arxiv.2311.01394","title":"Learning Realistic Traffic Agents in Closed-loop","display_name":"Learning Realistic Traffic Agents in Closed-loop","publication_year":2023,"publication_date":"2023-11-02","ids":{"openalex":"https://openalex.org/W4388327604","doi":"https://doi.org/10.48550/arxiv.2311.01394"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.01394","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.01394","pdf_url":"https://arxiv.org/pdf/2311.01394","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.01394","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100447801","display_name":"Wenjun Zhang","orcid":"https://orcid.org/0000-0001-7973-8769","observed_orcids":["https://orcid.org/0000-0001-7973-8769","https://orcid.org/0000-0001-8799-1182"]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhang, Chris","raw_affiliation_strings":["Waabi University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waabi University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000380827","display_name":"James Tu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tu, James","raw_affiliation_strings":["Waabi University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waabi University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054556065","display_name":"Lunjun Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zhang, Lunjun","raw_affiliation_strings":["Waabi University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waabi University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wong, Kelvin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wong, Kelvin","raw_affiliation_strings":["Waabi University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waabi University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Suo, Simon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Suo, Simon","raw_affiliation_strings":["Waabi University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waabi University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010469348","display_name":"Raquel Urtasun","orcid":"https://orcid.org/0000-0003-2332-5361","observed_orcids":["https://orcid.org/0000-0003-2332-5361"]},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Urtasun, Raquel","raw_affiliation_strings":["Waabi University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Waabi University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.7246000170707703,"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":0.7246000170707703,"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":0.2502000033855438,"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":0.007600000128149986,"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/traffic-simulation","display_name":"traffic simulation","score":0.5479999780654907},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.7269999980926514},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.9850000143051147},{"id":"https://openalex.org/keywords/closed-loop-learning","display_name":"closed-loop learning","score":0.8100000023841858},{"id":"https://openalex.org/keywords/long-tail-scenarios","display_name":"long-tail scenarios","score":0.6990000009536743},{"id":"https://openalex.org/keywords/traffic-forecasting","display_name":"traffic prediction","score":0.6010000109672546}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7839104533195496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7581976056098938},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.659868061542511},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.47591477632522583},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.4728662669658661},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4644361436367035},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.4491807520389557},{"id":"https://openalex.org/C2778391309","wikidata":"https://www.wikidata.org/wiki/Q7832527","display_name":"Traffic simulation","level":3,"score":0.42323219776153564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3889303207397461},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36588430404663086},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3396374583244324},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3229900300502777},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.16638219356536865},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.127170592546463},{"id":"https://openalex.org/C2780015235","wikidata":"https://www.wikidata.org/wiki/Q1934035","display_name":"Microsimulation","level":2,"score":0.1230892539024353},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.09375059604644775},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2311.01394","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.01394","pdf_url":"https://arxiv.org/pdf/2311.01394","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.01394","doi":"https://doi.org/10.48550/arxiv.2311.01394","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.01394","pdf_url":null,"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,"listed_in":[],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.01394","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.01394","pdf_url":"https://arxiv.org/pdf/2311.01394","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,"listed_in":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.7250000238418579,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"},{"score":0.5378999710083008,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388327604.pdf","grobid_xml":"https://content.openalex.org/works/W4388327604.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2782058284","https://openalex.org/W3103937890"],"abstract_inverted_index":{"Realistic":[0],"traffic":[1,28,41,77,108,158,169,191,203],"simulation":[2,159],"is":[3,23,61],"crucial":[4],"for":[5,185],"developing":[6],"self-driving":[7],"software":[8],"in":[9,63,87,131,171],"a":[10,97,107,116,181],"safe":[11],"and":[12,54,65,156,168,174],"scalable":[13],"manner":[14],"prior":[15],"to":[16,25,79,102,115,194,201],"real-world":[17,32,139],"deployment.":[18],"Typically,":[19],"imitation":[20],"learning":[21,73,100],"(IL)":[22],"used":[24,179],"learn":[26],"human-like":[27,166],"agents":[29,43,78],"directly":[30],"from":[31,45,138],"observations":[33],"collected":[34],"offline,":[35],"but":[36,82],"without":[37],"explicit":[38],"specification":[39],"of":[40,125,134],"rules,":[42],"trained":[44],"IL":[46,118],"alone":[47,85],"frequently":[48],"display":[49],"unrealistic":[50],"infractions":[51],"like":[52],"collisions":[53],"driving":[55,89,167],"off":[56],"the":[57,69,123,209],"road.":[58],"This":[59],"problem":[60],"exacerbated":[62],"out-of-distribution":[64],"long-tail":[66,146,175],"scenarios.":[67,147,176],"On":[68],"other":[70],"hand,":[71],"reinforcement":[72],"(RL)":[74],"can":[75],"train":[76],"avoid":[80],"infractions,":[81],"using":[83],"RL":[84,120],"results":[86],"unhuman-like":[88],"behaviors.":[90],"We":[91],"propose":[92],"Reinforcing":[93],"Traffic":[94],"Rules":[95],"(RTR),":[96],"holistic":[98],"closed-loop":[99,132],"objective":[101],"match":[103],"expert":[104],"demonstrations":[105],"under":[106],"compliance":[109,170],"constraint,":[110],"which":[111],"naturally":[112],"gives":[113],"rise":[114],"joint":[117],"+":[119],"approach,":[121],"obtaining":[122],"best":[124],"both":[126,135,172],"worlds.":[127],"Our":[128,148],"method":[129],"learns":[130,153],"simulations":[133],"nominal":[136,173],"scenarios":[137],"datasets":[140],"as":[141,143,180],"well":[142],"procedurally":[144],"generated":[145],"experiments":[149],"show":[150],"that":[151],"RTR":[152],"more":[154,206],"realistic":[155],"generalizable":[157],"policies,":[160],"achieving":[161],"significantly":[162],"better":[163],"tradeoffs":[164],"between":[165],"Moreover,":[177],"when":[178],"data":[182],"generation":[183],"tool":[184],"training":[186],"prediction":[187,198],"models,":[188],"our":[189],"learned":[190],"policy":[192],"leads":[193],"considerably":[195],"improved":[196],"downstream":[197],"metrics":[199],"compared":[200],"baseline":[202],"agents.":[204],"For":[205],"information,":[207],"visit":[208],"project":[210],"website:":[211],"https://waabi.ai/rtr":[212]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}