{"id":"https://openalex.org/W3120870661","doi":"https://doi.org/10.1109/iv47402.2020.9304594","title":"A New Approach for Tactical Decision Making in Lane Changing: Sample Efficient Deep Q Learning with a Safety Feedback Reward","display_name":"A New Approach for Tactical Decision Making in Lane Changing: Sample Efficient Deep Q Learning with a Safety Feedback Reward","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W3120870661","doi":"https://doi.org/10.1109/iv47402.2020.9304594","mag":"3120870661"},"language":"en","primary_location":{"id":"doi:10.1109/iv47402.2020.9304594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv47402.2020.9304594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"},"type":"article","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/A5002989669","display_name":"U\u011fur Yava\u015f","orcid":"https://orcid.org/0000-0003-1046-0142"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ugur Yavas","raw_affiliation_strings":["Eatron Technologies, Istanbul, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eatron Technologies, Istanbul, Turkey","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010725194","display_name":"Tufan Kumbasar","orcid":"https://orcid.org/0000-0001-9366-0240"},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Tufan Kumbasar","raw_affiliation_strings":["Istanbul Technical University, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Istanbul Technical University, Turkey","institution_ids":["https://openalex.org/I48912391"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028990507","display_name":"Naz\u0131m Kemal \u00dcre","orcid":"https://orcid.org/0000-0003-2660-2141"},"institutions":[{"id":"https://openalex.org/I48912391","display_name":"Istanbul Technical University","ror":"https://ror.org/059636586","country_code":"TR","type":"education","lineage":["https://openalex.org/I48912391"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Nazim Kemal Ure","raw_affiliation_strings":["Artificial Intelligence and Data Science Research Center, Istanbul Technical University, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Data Science Research Center, Istanbul Technical University, Turkey","institution_ids":["https://openalex.org/I48912391"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4263,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.82034031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1156","last_page":"1161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9986000061035156,"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":0.9941999912261963,"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/intuition","display_name":"Intuition","score":0.8413150310516357},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.8279685974121094},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7554892301559448},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5930427312850952},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5278520584106445},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5193966031074524},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.478089302778244},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4457463026046753},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3726590573787689},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12143227458000183}],"concepts":[{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.8413150310516357},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.8279685974121094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554892301559448},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5930427312850952},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5278520584106445},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5193966031074524},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.478089302778244},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4457463026046753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3726590573787689},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12143227458000183},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iv47402.2020.9304594","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iv47402.2020.9304594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE Intelligent Vehicles Symposium (IV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3944142147","display_name":null,"funder_award_id":"118E807","funder_id":"https://openalex.org/F4320322626","funder_display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu"}],"funders":[{"id":"https://openalex.org/F4320322626","display_name":"T\u00fcrkiye Bilimsel ve Teknolojik Ara\u015ft\u0131rma Kurumu","ror":"https://ror.org/04w9kkr77"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W631263868","https://openalex.org/W1626155273","https://openalex.org/W1965455100","https://openalex.org/W2011931151","https://openalex.org/W2056877664","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2242368318","https://openalex.org/W2257979135","https://openalex.org/W2406067508","https://openalex.org/W2537623947","https://openalex.org/W2575705757","https://openalex.org/W2740361510","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2787196707","https://openalex.org/W2795064979","https://openalex.org/W2904263972","https://openalex.org/W2949576341","https://openalex.org/W2989958156","https://openalex.org/W2990417263","https://openalex.org/W3100789280","https://openalex.org/W3102777717","https://openalex.org/W4288560585","https://openalex.org/W6748571143"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2987774938","https://openalex.org/W2352448290","https://openalex.org/W4256492088"],"abstract_inverted_index":{"Automated":[0],"lane":[1],"change":[2],"is":[3,98,107],"one":[4],"of":[5,13,31,34,72,94,113,117],"the":[6,28,32,52,77,83,91,104,111,118,127,131],"most":[7],"challenging":[8,132],"task":[9],"to":[10,18,50,66,126,141],"be":[11],"solved":[12],"highly":[14],"automated":[15],"vehicles":[16],"due":[17],"its":[19],"safety-critical,":[20],"uncertain":[21,58],"and":[22,57,86],"multi-agent":[23],"nature.":[24],"This":[25],"paper":[26],"presents":[27],"novel":[29,70,92],"deployment":[30,93],"state":[33],"art":[35],"Q":[36,115],"learning":[37],"method,":[38],"namely":[39],"Rainbow":[40,95],"DQN,":[41,96],"that":[42,68,100],"uses":[43],"a":[44],"new":[45],"safety":[46,78],"driven":[47],"rewarding":[48],"scheme":[49],"tackle":[51],"issues":[53],"in":[54,130],"an":[55],"dynamic":[56],"simulation":[59],"environment.":[60],"We":[61],"present":[62],"various":[63],"comparative":[64],"results":[65],"show":[67],"our":[69],"approach":[71],"having":[73],"reward":[74],"feedback":[75],"from":[76],"layer":[79],"dramatically":[80],"increases":[81],"both":[82],"agent's":[84,105],"performance":[85,125],"sample":[87],"efficiency.":[88],"Furthermore,":[89],"through":[90],"it":[97],"shown":[99],"more":[101],"intuition":[102],"about":[103],"actions":[106],"extracted":[108],"by":[109],"examining":[110],"distributions":[112],"generated":[114],"values":[116],"agents.":[119],"The":[120],"proposed":[121],"algorithm":[122,129],"shows":[123],"superior":[124],"baseline":[128],"scenarios":[133],"with":[134],"only":[135],"200000":[136],"training":[137],"steps":[138],"(i.e.":[139],"equivalent":[140],"55":[142],"hours":[143],"driving).":[144]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}