{"id":"https://openalex.org/W3027509799","doi":"https://doi.org/10.1109/itsc45102.2020.9294338","title":"Reinforcement Learning with Iterative Reasoning for Merging in Dense Traffic","display_name":"Reinforcement Learning with Iterative Reasoning for Merging in Dense Traffic","publication_year":2020,"publication_date":"2020-09-20","ids":{"openalex":"https://openalex.org/W3027509799","doi":"https://doi.org/10.1109/itsc45102.2020.9294338","mag":"3027509799"},"language":"en","primary_location":{"id":"doi:10.1109/itsc45102.2020.9294338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc45102.2020.9294338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2005.11895","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003495895","display_name":"Maxime Bouton","orcid":"https://orcid.org/0000-0002-9151-1513"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxime Bouton","raw_affiliation_strings":["Stanford University, Stanford, CA, USA","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050227531","display_name":"Alireza Nakhaei","orcid":"https://orcid.org/0000-0001-9318-9372"},"institutions":[{"id":"https://openalex.org/I4391768151","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210125472","https://openalex.org/I4391768151"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alireza Nakhaei","raw_affiliation_strings":["Toyota Research Institute, 4440 El Camino Real, Los Altos, CA, USA","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toyota Research Institute, 4440 El Camino Real, Los Altos, CA, USA","institution_ids":["https://openalex.org/I4391768151"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063634505","display_name":"David Isele","orcid":"https://orcid.org/0000-0001-9749-6951"},"institutions":[{"id":"https://openalex.org/I4210145184","display_name":"Honda (United States)","ror":"https://ror.org/04vdmc602","country_code":"US","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210145184"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Isele","raw_affiliation_strings":["Honda Research Institute, Mountain View, CA, USA","Honda Research Institute,Mountain View,CA,USA,94043"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210145184"]},{"raw_affiliation_string":"Honda Research Institute,Mountain View,CA,USA,94043","institution_ids":["https://openalex.org/I4210145184"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112249344","display_name":"Kikuo Fujimura","orcid":null},"institutions":[{"id":"https://openalex.org/I4210145184","display_name":"Honda (United States)","ror":"https://ror.org/04vdmc602","country_code":"US","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210145184"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kikuo Fujimura","raw_affiliation_strings":["Honda Research Institute, Mountain View, CA, USA","Honda Research Institute,Mountain View,CA,USA,94043"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute, Mountain View, CA, USA","institution_ids":["https://openalex.org/I4210145184"]},{"raw_affiliation_string":"Honda Research Institute,Mountain View,CA,USA,94043","institution_ids":["https://openalex.org/I4210145184"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068326377","display_name":"Mykel J. Kochenderfer","orcid":"https://orcid.org/0000-0002-7238-9663"},"institutions":[{"id":"https://openalex.org/I13805885","display_name":"Vaughn College of Aeronautics and Technology","ror":"https://ror.org/056e22e24","country_code":"US","type":"education","lineage":["https://openalex.org/I13805885"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mykel J. Kochenderfer","raw_affiliation_strings":["Stanford University, Stanford, CA, USA","Stanford University,,Department of Aeronautics and Astronautics,Stanford,CA,USA,94305"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University,,Department of Aeronautics and Astronautics,Stanford,CA,USA,94305","institution_ids":["https://openalex.org/I13805885","https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.06186026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9993000030517578,"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":0.9993000030517578,"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/T10524","display_name":"Traffic control and management","score":0.9987000226974487,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.995199978351593,"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":0.9187173843383789},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7331770658493042},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6819038391113281},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.666644275188446},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5696181654930115},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45728155970573425},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4055692255496979},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11748072504997253}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9187173843383789},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7331770658493042},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6819038391113281},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.666644275188446},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5696181654930115},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45728155970573425},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4055692255496979},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11748072504997253},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/itsc45102.2020.9294338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc45102.2020.9294338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2005.11895","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.11895","pdf_url":"https://arxiv.org/pdf/2005.11895","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2005.11895","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2005.11895","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,"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":"article-journal"},{"id":"mag:3027509799","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2005.11895","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2005.11895","pdf_url":"https://arxiv.org/pdf/2005.11895","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3027509799.pdf","grobid_xml":"https://content.openalex.org/works/W3027509799.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1965455100","https://openalex.org/W2017443480","https://openalex.org/W2056877664","https://openalex.org/W2067050450","https://openalex.org/W2082585576","https://openalex.org/W2115211925","https://openalex.org/W2120575449","https://openalex.org/W2145339207","https://openalex.org/W2155014708","https://openalex.org/W2173564293","https://openalex.org/W2545546008","https://openalex.org/W2767617058","https://openalex.org/W2897752552","https://openalex.org/W2904937669","https://openalex.org/W2909414402","https://openalex.org/W2963477884","https://openalex.org/W2963575966","https://openalex.org/W2963804019","https://openalex.org/W2963937357","https://openalex.org/W2968077992","https://openalex.org/W2970787054","https://openalex.org/W2973183361","https://openalex.org/W2989958156","https://openalex.org/W2989964169","https://openalex.org/W2991589230","https://openalex.org/W3023932353","https://openalex.org/W3045909318","https://openalex.org/W3091516903","https://openalex.org/W3124871979","https://openalex.org/W3148740559","https://openalex.org/W6677067356","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6743367460","https://openalex.org/W6746141047"],"related_works":["https://openalex.org/W3116294947","https://openalex.org/W2896183040","https://openalex.org/W3186035148","https://openalex.org/W3094234915","https://openalex.org/W2614018942","https://openalex.org/W2105741987","https://openalex.org/W3096763169","https://openalex.org/W2978985043","https://openalex.org/W3209943843","https://openalex.org/W1604959332","https://openalex.org/W1533061407","https://openalex.org/W2809097245","https://openalex.org/W2020573190","https://openalex.org/W2979628718","https://openalex.org/W187126577","https://openalex.org/W3091126461","https://openalex.org/W2883869105","https://openalex.org/W3008102108","https://openalex.org/W2995736683","https://openalex.org/W3120102699"],"abstract_inverted_index":{"Maneuvering":[0],"in":[1],"dense":[2],"traffic":[3],"is":[4],"a":[5,32,42,56,60,76],"challenging":[6],"task":[7],"for":[8,59],"autonomous":[9],"vehicles":[10],"because":[11],"it":[12],"requires":[13],"reasoning":[14],"about":[15],"the":[16,25,29,65,73],"stochastic":[17],"behaviors":[18,80],"of":[19,44,67,79],"many":[20],"other":[21],"participants.":[22],"In":[23,37],"addition,":[24],"agent":[26,63,74],"must":[27],"achieve":[28],"maneuver":[30],"within":[31],"limited":[33],"time":[34],"and":[35,47],"distance.":[36],"this":[38],"work,":[39],"we":[40],"propose":[41],"combination":[43],"reinforcement":[45,61],"learning":[46,62,85],"game":[48],"theory":[49],"to":[50,75,90],"learn":[51],"merging":[52],"behaviors.":[53],"We":[54,93],"design":[55],"training":[57,104],"curriculum":[58],"using":[64],"concept":[66],"level-k":[68],"behavior.":[69],"This":[70],"approach":[71,97],"exposes":[72],"broad":[77],"variety":[78],"during":[81],"training,":[82],"which":[83],"promotes":[84],"policies":[86,101],"that":[87,95],"are":[88],"robust":[89],"model":[91],"discrepancies.":[92],"show":[94],"our":[96],"learns":[98],"more":[99],"efficient":[100],"than":[102],"traditional":[103],"methods.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2022-07-26T00:00:00"}