{"id":"https://openalex.org/W3209381383","doi":"https://doi.org/10.1109/itsc48978.2021.9564972","title":"Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement Learning","display_name":"Quick Learner Automated Vehicle Adapting its Roadmanship to Varying Traffic Cultures with Meta Reinforcement Learning","publication_year":2021,"publication_date":"2021-09-19","ids":{"openalex":"https://openalex.org/W3209381383","doi":"https://doi.org/10.1109/itsc48978.2021.9564972","mag":"3209381383"},"language":"en","primary_location":{"id":"doi:10.1109/itsc48978.2021.9564972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc48978.2021.9564972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045427668","display_name":"Songan Zhang","orcid":"https://orcid.org/0000-0002-3238-5406"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songan Zhang","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109870380","display_name":"Lu Wen","orcid":"https://orcid.org/0009-0006-5558-2820"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lu Wen","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019025642","display_name":"Huei Peng","orcid":"https://orcid.org/0000-0002-1844-3163"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huei Peng","raw_affiliation_strings":["University of Michigan, Ann Arbor, MI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, MI, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034788095","display_name":"H. Eric Tseng","orcid":"https://orcid.org/0000-0001-9544-4226"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H. Eric Tseng","raw_affiliation_strings":["Ford Motor Company"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ford Motor Company","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1745","last_page":"1752"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.9961000084877014,"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":0.9958999752998352,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9314879775047302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7456581592559814},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6962728500366211},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6908756494522095},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.5780230164527893},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.494686096906662},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4540087878704071},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4289950430393219},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.41659754514694214},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3886792063713074},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.36829277873039246},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19292083382606506},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.07272481918334961}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9314879775047302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7456581592559814},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6962728500366211},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6908756494522095},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.5780230164527893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.494686096906662},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4540087878704071},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4289950430393219},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.41659754514694214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3886792063713074},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.36829277873039246},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19292083382606506},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07272481918334961},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc48978.2021.9564972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc48978.2021.9564972","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Intelligent Transportation Systems Conference (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W1977655452","https://openalex.org/W2061562262","https://openalex.org/W2091440166","https://openalex.org/W2142620093","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2291973609","https://openalex.org/W2550182557","https://openalex.org/W2578206533","https://openalex.org/W2580175322","https://openalex.org/W2604763608","https://openalex.org/W2610332124","https://openalex.org/W2755546070","https://openalex.org/W2781726626","https://openalex.org/W2788084076","https://openalex.org/W2788904251","https://openalex.org/W2923504512","https://openalex.org/W2949676527","https://openalex.org/W2952526277","https://openalex.org/W2962732055","https://openalex.org/W2962974944","https://openalex.org/W2962991582","https://openalex.org/W2963438456","https://openalex.org/W2963581679","https://openalex.org/W2963703448","https://openalex.org/W2963748792","https://openalex.org/W2964340170","https://openalex.org/W2966697668","https://openalex.org/W2990116160","https://openalex.org/W2991448601","https://openalex.org/W3007923353","https://openalex.org/W3036152059","https://openalex.org/W3103559770","https://openalex.org/W3115648115","https://openalex.org/W4288363736","https://openalex.org/W4289388948","https://openalex.org/W4294562617","https://openalex.org/W4300427683","https://openalex.org/W4300971732","https://openalex.org/W6638018090","https://openalex.org/W6680987537","https://openalex.org/W6736057607","https://openalex.org/W6744181227","https://openalex.org/W6747473740","https://openalex.org/W6748460798","https://openalex.org/W6760698134","https://openalex.org/W6766755266","https://openalex.org/W6774197901"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W4294873804"],"abstract_inverted_index":{"It":[0],"is":[1],"essential":[2],"for":[3],"an":[4],"automated":[5,55],"vehicle":[6,56],"in":[7,48,106],"the":[8,114],"field":[9],"to":[10,54,65,68,95,112],"perform":[11],"discretionary":[12],"lane":[13],"changes":[14],"with":[15,71],"appropriate":[16],"roadmanship":[17],"-":[18,30],"driving":[19,39,57,93,121],"safely":[20],"and":[21,38,51,87,110],"efficiently":[22],"without":[23],"annoying":[24],"or":[25],"endangering":[26],"other":[27],"road":[28],"users":[29],"under":[31],"a":[32,80,126],"wide":[33],"range":[34],"of":[35,103,118],"traffic":[36,70],"cultures":[37],"conditions.":[40],"While":[41],"deep":[42],"reinforcement":[43],"learning":[44,99],"methods":[45],"have":[46],"excelled":[47],"recent":[49],"years":[50],"been":[52],"applied":[53],"policy,":[58],"there":[59],"are":[60],"concerns":[61],"about":[62],"their":[63,97],"capability":[64,117],"quickly":[66],"adapt":[67],"unseen":[69],"new":[72],"environment":[73],"dynamics.":[74],"We":[75],"formulate":[76],"this":[77],"challenge":[78],"as":[79],"multi-Markov":[81],"Decision":[82],"Processes":[83],"(MDPs)":[84],"adaptation":[85,116],"problem":[86],"developed":[88],"Meta":[89],"Reinforcement":[90],"Learning":[91],"(MRL)":[92],"policies":[94,122],"showcase":[96],"quick":[98],"capability.":[100],"Two":[101],"types":[102],"distribution":[104],"variation":[105],"environments":[107],"were":[108],"designed":[109],"simulated":[111],"validate":[113],"fast":[115],"resulting":[119],"MRL":[120],"which":[123],"significantly":[124],"outperform":[125],"baseline":[127],"RL.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}