{"id":"https://openalex.org/W2973183361","doi":"https://doi.org/10.1109/icra40945.2020.9197132","title":"Driving in Dense Traffic with Model-Free Reinforcement Learning","display_name":"Driving in Dense Traffic with Model-Free Reinforcement Learning","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W2973183361","doi":"https://doi.org/10.1109/icra40945.2020.9197132","mag":"2973183361"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197132","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1909.06710","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Dhruv Mauria Saxena","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dhruv Mauria Saxena","raw_affiliation_strings":["Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sangjae Bae","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sangjae Bae","raw_affiliation_strings":["University of California, Berkeley, USA"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Alireza Nakhaei","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":"Alireza Nakhaei","raw_affiliation_strings":["Honda Research Institute USA, Inc"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute USA, Inc","institution_ids":["https://openalex.org/I4210145184"]}]},{"author_position":"middle","author":{"id":null,"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 USA, Inc"],"affiliations":[{"raw_affiliation_string":"Honda Research Institute USA, Inc","institution_ids":["https://openalex.org/I4210145184"]}]},{"author_position":"last","author":{"id":null,"display_name":"Maxim Likhachev","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxim Likhachev","raw_affiliation_strings":["Carnegie Mellon University, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":6.8258,"has_fulltext":false,"cited_by_count":78,"citation_normalized_percentile":{"value":0.97383131,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5385","last_page":"5392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9993000030517578,"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":0.9993000030517578,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9987999796867371,"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":0.9944999814033508,"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":0.8284000158309937},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.5828999876976013},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44040000438690186},{"id":"https://openalex.org/keywords/negotiation","display_name":"Negotiation","score":0.42899999022483826},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42089998722076416},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41679999232292175},{"id":"https://openalex.org/keywords/weaving","display_name":"Weaving","score":0.36010000109672546},{"id":"https://openalex.org/keywords/drone","display_name":"Drone","score":0.3497999906539917}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8284000158309937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6776000261306763},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.5828999876976013},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44040000438690186},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4334000051021576},{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.42899999022483826},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42089998722076416},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C54525549","wikidata":"https://www.wikidata.org/wiki/Q2553445","display_name":"Weaving","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C2778391309","wikidata":"https://www.wikidata.org/wiki/Q7832527","display_name":"Traffic simulation","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.2743000090122223},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C2780864053","wikidata":"https://www.wikidata.org/wiki/Q5147495","display_name":"Collision avoidance","level":3,"score":0.25130000710487366},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icra40945.2020.9197132","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197132","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1909.06710","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.06710","pdf_url":"https://arxiv.org/pdf/1909.06710","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1909.06710","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1909.06710","pdf_url":"https://arxiv.org/pdf/1909.06710","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W198912494","https://openalex.org/W1592601589","https://openalex.org/W1945187479","https://openalex.org/W1965455100","https://openalex.org/W1977085960","https://openalex.org/W2082585576","https://openalex.org/W2119112357","https://openalex.org/W2139137304","https://openalex.org/W2163411428","https://openalex.org/W2192586580","https://openalex.org/W2343568200","https://openalex.org/W2411577903","https://openalex.org/W2505763307","https://openalex.org/W2530849036","https://openalex.org/W2580495915","https://openalex.org/W2729776805","https://openalex.org/W2733312032","https://openalex.org/W2739529772","https://openalex.org/W2783963507","https://openalex.org/W2793753444","https://openalex.org/W2899160681","https://openalex.org/W2911087563","https://openalex.org/W2962894046","https://openalex.org/W2963001155","https://openalex.org/W2969076652","https://openalex.org/W2989958156","https://openalex.org/W2990123902","https://openalex.org/W3004268170","https://openalex.org/W3100366369","https://openalex.org/W6651853181","https://openalex.org/W6684338915","https://openalex.org/W6684921986","https://openalex.org/W6704559304","https://openalex.org/W6741002519","https://openalex.org/W6741471465","https://openalex.org/W6758417531","https://openalex.org/W6767599690"],"related_works":[],"abstract_inverted_index":{"Traditional":[0],"planning":[1],"and":[2,119,142,186],"control":[3,123],"methods":[4,78],"could":[5],"fail":[6,79],"to":[7,16,40,57,60,72,80,114,140,151,160,170,175],"find":[8,171],"a":[9,74,121,144,172,202],"feasible":[10],"trajectory":[11],"for":[12,37,204,209],"an":[13,91,130],"autonomous":[14,131],"vehicle":[15,39],"execute":[17],"amongst":[18,62],"dense":[19,63,207],"traffic":[20,64,208],"on":[21,99,107],"roads.":[22],"This":[23],"is":[24,31,50],"because":[25],"the":[26,38,48,67,84,87,94,100,108,126,147,164,212],"obstacle-free":[27],"volume":[28],"in":[29,34,146,149,177,193,206],"spacetime":[30],"very":[32],"small":[33],"these":[35],"scenarios":[36],"drive":[41,61],"through.":[42],"However,":[43],"that":[44,86,188],"does":[45],"not":[46],"mean":[47],"task":[49],"infeasible":[51],"since":[52],"human":[53],"drivers":[54,71],"are":[55],"known":[56],"be":[58],"able":[59],"by":[65,90,211],"leveraging":[66],"cooperativeness":[68],"of":[69,96,110,129,197],"other":[70,97],"open":[73,143],"gap.":[75],"The":[76,133],"traditional":[77],"take":[81],"into":[82,163],"account":[83],"fact":[85],"actions":[88],"taken":[89],"agent":[92,139],"affect":[93],"behaviour":[95],"vehicles":[98],"road.":[101],"In":[102],"this":[103,198],"work,":[104,199],"we":[105,135,200],"rely":[106],"ability":[109],"deep":[111],"reinforcement":[112],"learning":[113],"implicitly":[115],"model":[116],"such":[117],"interactions":[118],"learn":[120],"continuous":[122],"policy":[124,158,190],"over":[125],"action":[127],"space":[128],"vehicle.":[132],"application":[134],"consider":[136],"requires":[137],"our":[138,189],"negotiate":[141],"gap":[145],"road":[148,166],"order":[150],"successfully":[152],"merge":[153],"or":[154],"change":[155],"lanes.":[156],"Our":[157],"learns":[159],"repeatedly":[161],"probe":[162],"target":[165],"lane":[167],"while":[168],"trying":[169],"safe":[173],"spot":[174],"move":[176],"to.":[178],"We":[179],"compare":[180],"against":[181],"two":[182],"model-predictive":[183],"control-based":[184],"algorithms":[185],"show":[187],"outperforms":[191],"them":[192],"simulation.":[194],"As":[195],"part":[196],"introduce":[201],"benchmark":[203],"driving":[205],"use":[210],"community.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2019-09-19T00:00:00"}