{"id":"https://openalex.org/W3081943343","doi":"https://doi.org/10.1109/iv48863.2021.9575379","title":"Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles","display_name":"Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles","publication_year":2021,"publication_date":"2021-07-11","ids":{"openalex":"https://openalex.org/W3081943343","doi":"https://doi.org/10.1109/iv48863.2021.9575379","mag":"3081943343"},"language":"en","primary_location":{"id":"doi:10.1109/iv48863.2021.9575379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv48863.2021.9575379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2008.12451","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100357227","display_name":"Fei Ye","orcid":"https://orcid.org/0000-0002-8875-4186"},"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":true,"raw_author_name":"Fei Ye","raw_affiliation_strings":["California PATH, University of California, Berkeley,Richmond,CA,USA,94804"],"affiliations":[{"raw_affiliation_string":"California PATH, University of California, Berkeley,Richmond,CA,USA,94804","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100735652","display_name":"Pin Wang","orcid":"https://orcid.org/0000-0002-1400-4497"},"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":"Pin Wang","raw_affiliation_strings":["California PATH, University of California, Berkeley,Richmond,CA,USA,94804"],"affiliations":[{"raw_affiliation_string":"California PATH, University of California, Berkeley,Richmond,CA,USA,94804","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014661259","display_name":"Ching\u2010Yao Chan","orcid":"https://orcid.org/0000-0003-3992-2312"},"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":"Ching-Yao Chan","raw_affiliation_strings":["California PATH, University of California, Berkeley,Richmond,CA,USA,94804"],"affiliations":[{"raw_affiliation_string":"California PATH, University of California, Berkeley,Richmond,CA,USA,94804","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014940997","display_name":"Jiucai Zhang","orcid":"https://orcid.org/0000-0002-6245-9736"},"institutions":[{"id":"https://openalex.org/I4210148712","display_name":"Silicon Valley University","ror":"https://ror.org/04jk6hn97","country_code":"US","type":"education","lineage":["https://openalex.org/I4210148712"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiucai Zhang","raw_affiliation_strings":["GAC R&D Center Silicon Valley Inc.,Sunnyvale,CA,USA,94085","GAC R&D Center Silicon Valley Inc.,Sunnyvale,CA,USA,94085"],"affiliations":[{"raw_affiliation_string":"GAC R&D Center Silicon Valley Inc.,Sunnyvale,CA,USA,94085","institution_ids":["https://openalex.org/I4210148712"]},{"raw_affiliation_string":"GAC R&D Center Silicon Valley Inc.,Sunnyvale,CA,USA,94085","institution_ids":["https://openalex.org/I4210148712"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100357227"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.1853,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.46471868,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"223","last_page":"230"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983999729156494,"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":0.9944999814033508,"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":0.8763008117675781},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7720226049423218},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7543306350708008},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6025451421737671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5611183047294617},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5255857110023499},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.443711519241333},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.43734848499298096}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8763008117675781},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7720226049423218},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7543306350708008},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6025451421737671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5611183047294617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5255857110023499},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.443711519241333},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.43734848499298096},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iv48863.2021.9575379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv48863.2021.9575379","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2008.12451","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.12451","pdf_url":"https://arxiv.org/pdf/2008.12451","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"},{"id":"doi:10.48550/arxiv.2008.12451","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2008.12451","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3081943343","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:2008.12451","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2008.12451","pdf_url":"https://arxiv.org/pdf/2008.12451","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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3081943343.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W24067677","https://openalex.org/W1522301498","https://openalex.org/W1542791059","https://openalex.org/W1575592356","https://openalex.org/W1965455100","https://openalex.org/W2119717200","https://openalex.org/W2306644740","https://openalex.org/W2343568200","https://openalex.org/W2550182557","https://openalex.org/W2578206533","https://openalex.org/W2583993537","https://openalex.org/W2604763608","https://openalex.org/W2626860042","https://openalex.org/W2736601468","https://openalex.org/W2736629007","https://openalex.org/W2751422670","https://openalex.org/W2788904251","https://openalex.org/W2795064979","https://openalex.org/W2904263972","https://openalex.org/W2905173465","https://openalex.org/W2938321354","https://openalex.org/W2952194250","https://openalex.org/W2953303875","https://openalex.org/W2962974944","https://openalex.org/W2963322416","https://openalex.org/W2969758225","https://openalex.org/W2981207549","https://openalex.org/W2991052353","https://openalex.org/W3005504700","https://openalex.org/W3100944043","https://openalex.org/W3102777717","https://openalex.org/W6631190155","https://openalex.org/W6634413486","https://openalex.org/W6729433768","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6741002519","https://openalex.org/W6748600884","https://openalex.org/W6756463683","https://openalex.org/W6756871163","https://openalex.org/W6773613285"],"related_works":["https://openalex.org/W3009357917","https://openalex.org/W3086530824","https://openalex.org/W2626860042","https://openalex.org/W3034552332","https://openalex.org/W2904263972","https://openalex.org/W2944397927","https://openalex.org/W2944714385","https://openalex.org/W3207250575","https://openalex.org/W3151079898","https://openalex.org/W2980297462","https://openalex.org/W3191652410","https://openalex.org/W3030598573","https://openalex.org/W3154065671","https://openalex.org/W2885445959","https://openalex.org/W3129896193","https://openalex.org/W3094188159","https://openalex.org/W2950622182","https://openalex.org/W3023661178","https://openalex.org/W3210638693","https://openalex.org/W2906917062"],"abstract_inverted_index":{"The":[0,105,229],"field":[1],"of":[2,10,159,169,225,270],"autonomous":[3,24],"driving":[4,25],"has":[5],"seen":[6],"increasing":[7],"proposed":[8,171,192,202,246],"use":[9,152],"machine":[11],"learning":[12,35,40,65,93,132],"methodologies.":[13],"However,":[14],"there":[15],"are":[16,143],"still":[17,78],"challenges":[18],"in":[19,43,46,80],"applying":[20],"such":[21,37],"methods":[22,66],"since":[23],"involves":[26],"complex":[27],"and":[28,73,134,156,167,187,251,255,261],"dynamic":[29],"interactions":[30],"with":[31,240,265],"the":[32,47,69,98,121,160,165,170,183,201,214,222,241,245],"environment.":[33],"Supervised":[34],"algorithms":[36],"as":[38,178,190],"imitation":[39],"can":[41,67,256],"work":[42],"environments":[44],"represented":[45],"training":[48,188],"data":[49,59],"set,":[50],"however,":[51],"it":[52,76,137,218],"is":[53,107,176,219,232],"impractical":[54],"or":[55],"cost-prohibitive":[56],"to":[57,96,102,109,125,163,210,221,237],"collect":[58],"for":[60,194],"all":[61],"possible":[62],"environments.":[63,82,104],"Reinforcement":[64],"train":[68,120],"agent":[70],"through":[71],"trial":[72],"error,":[74],"but":[75],"may":[77],"fail":[79],"new":[81,103,223],"To":[83],"overcome":[84],"these":[85],"shortcomings,":[86],"we":[87,119,151],"thus":[88],"propose":[89],"a":[90,130,179,267],"meta":[91],"reinforcement":[92,131],"(MRL)":[94],"method":[95,106,203],"improve":[97],"agent's":[99],"generalization":[100],"capabilities":[101,254],"applied":[108],"automated":[110],"lane-changing":[111],"maneuvers":[112,162],"at":[113,123,138],"different":[114],"traffic":[115,127,140,227],"congestion":[116],"levels.":[117],"Specifically,":[118],"model":[122,175,193,216,247],"light":[124],"moderate":[126],"conditions":[128,141],"under":[129],"framework,":[133],"then":[135],"test":[136],"heavy":[139,226],"that":[142,200],"never":[144],"encountered":[145],"during":[146],"training.":[147],"For":[148],"performance":[149],"evaluation,":[150],"both":[153],"collision":[154,230,263],"rate":[155,158,208,231,260,264],"success":[157,207],"lane-change":[161],"quantify":[164],"safety":[166],"effectiveness":[168],"model.":[172,243],"A":[173],"pretrained":[174],"established":[177],"benchmark,":[180],"which":[181],"uses":[182],"same":[184],"network":[185],"structure":[186],"tasks":[189],"our":[191],"fair":[195],"comparison.":[196],"Simulation":[197],"results":[198],"show":[199],"achieves":[204],"an":[205],"overall":[206],"up":[209,236],"20%":[211],"higher":[212],"than":[213],"benchmark":[215,242],"when":[217],"generalized":[220],"environment":[224],"density.":[228],"also":[233],"reduced":[234],"by":[235],"18%":[238],"compared":[239],"Furthermore,":[244],"shows":[248],"more":[249],"stable":[250],"efficient":[252],"adaptation":[253],"achieve":[257],"100%":[258],"successful":[259],"0%":[262],"only":[266],"few":[268],"steps":[269],"gradient":[271],"update":[272],"adaptation.":[273]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}