{"id":"https://openalex.org/W4385256953","doi":"https://doi.org/10.1109/tits.2023.3292981","title":"A Real-World Reinforcement Learning Framework for Safe and Human-Like Tactical Decision-Making","display_name":"A Real-World Reinforcement Learning Framework for Safe and Human-Like Tactical Decision-Making","publication_year":2023,"publication_date":"2023-07-25","ids":{"openalex":"https://openalex.org/W4385256953","doi":"https://doi.org/10.1109/tits.2023.3292981"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2023.3292981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2023.3292981","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-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/A5065740650","display_name":"M. Ugur Yavas","orcid":"https://orcid.org/0000-0002-6192-4472"},"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":"Muharrem Ugur Yavas","raw_affiliation_strings":["Department of Mechatronics Engineering, Istanbul Technical University, Istanbul, Turkey","Eatron Technologies, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-6192-4472","affiliations":[{"raw_affiliation_string":"Department of Mechatronics Engineering, Istanbul Technical University, Istanbul, Turkey","institution_ids":["https://openalex.org/I48912391"]},{"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":["Department of Control and Automation Engineering, Istanbul Technical University, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-9366-0240","affiliations":[{"raw_affiliation_string":"Department of Control and Automation Engineering, Istanbul Technical University, Istanbul, 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, Istanbul, Turkey"],"raw_orcid":"https://orcid.org/0000-0003-2660-2141","affiliations":[{"raw_affiliation_string":"Artificial Intelligence and Data Science Research Center, Istanbul Technical University, Istanbul, 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":1.5505,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.82098243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"24","issue":"11","first_page":"11773","last_page":"11784"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9988999962806702,"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":0.9988999962806702,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9894999861717224,"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":0.7678967714309692},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5081262588500977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4543643593788147},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.3874879479408264},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3254525065422058},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.32493144273757935}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7678967714309692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5081262588500977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4543643593788147},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3874879479408264},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3254525065422058},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.32493144273757935}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2023.3292981","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2023.3292981","pdf_url":null,"source":{"id":"https://openalex.org/S144771191","display_name":"IEEE Transactions on Intelligent Transportation Systems","issn_l":"1524-9050","issn":["1524-9050","1558-0016"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Intelligent Transportation Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322628","display_name":"T\u00fcrkiye Bilimler Akademisi","ror":"https://ror.org/00aqt9352"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1592601589","https://openalex.org/W1626155273","https://openalex.org/W1911469587","https://openalex.org/W1919962963","https://openalex.org/W1965455100","https://openalex.org/W2011931151","https://openalex.org/W2056877664","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2162489854","https://openalex.org/W2170973929","https://openalex.org/W2201581102","https://openalex.org/W2342840547","https://openalex.org/W2523230182","https://openalex.org/W2537623947","https://openalex.org/W2575705757","https://openalex.org/W2740361510","https://openalex.org/W2786928559","https://openalex.org/W2795064979","https://openalex.org/W2811374584","https://openalex.org/W2883265831","https://openalex.org/W2904263972","https://openalex.org/W2989958156","https://openalex.org/W2990417263","https://openalex.org/W3044015199","https://openalex.org/W3088310808","https://openalex.org/W3102777717","https://openalex.org/W3115502595","https://openalex.org/W3115696625","https://openalex.org/W3120778962","https://openalex.org/W3120870661","https://openalex.org/W3121342653","https://openalex.org/W3127561923","https://openalex.org/W3205019221","https://openalex.org/W4214717370","https://openalex.org/W6687681856","https://openalex.org/W6704559304","https://openalex.org/W6748554570","https://openalex.org/W6748571143","https://openalex.org/W6752963931","https://openalex.org/W6753505025","https://openalex.org/W6787289735","https://openalex.org/W6787476729","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Lane-change":[0],"decision-making":[1,84],"for":[2,8,36,83,107],"vehicles":[3],"is":[4,146,173,200],"a":[5,79,103,140,149,160],"challenging":[6],"task":[7],"many":[9],"reasons,":[10],"including":[11],"traffic":[12],"rules,":[13],"safety,":[14],"and":[15,55,71,74,88,117,177,182],"the":[16,41,62,67,95,138,153,168,171,186,189,193,196,201,209],"stochastic":[17],"nature":[18],"of":[19,22,129,143,188,195,204],"driving.":[20],"Because":[21],"its":[23],"success":[24],"in":[25,53,94,159,167,208],"solving":[26],"complex":[27],"problems,":[28],"deep":[29],"reinforcement":[30],"learning":[31,105],"(DRL)":[32],"has":[33],"been":[34],"suggested":[35],"addressing":[37],"these":[38],"issues.":[39],"However,":[40],"studies":[42],"on":[43],"DRL":[44,81,108,205],"to":[45,57,85,163],"date":[46],"have":[47],"gone":[48],"no":[49],"further":[50],"than":[51],"validation":[52],"simulation":[54,70,181],"failed":[56],"address":[58],"what":[59],"are":[60,132,156],"arguably":[61],"most":[63],"critical":[64],"issues,":[65],"namely,":[66],"mismatch":[68],"between":[69],"reality,":[72],"human-likeness,":[73],"safety.":[75],"This":[76],"paper":[77],"introduces":[78],"real-world":[80,135,183],"framework":[82],"design":[86],"safe":[87],"human-like":[89,178],"agents":[90],"that":[91],"can":[92],"operate":[93],"real":[96,210],"world":[97],"without":[98],"extra":[99],"tuning.":[100],"We":[101],"propose":[102],"new":[104],"paradigm":[106],"integrated":[109],"with":[110,126,148],"Real2Sim":[111],"transfer,":[112],"which":[113,131],"comprises":[114],"training,":[115],"validation,":[116],"testing":[118,169],"phases.":[119],"The":[120],"approach":[121],"involves":[122],"two":[123],"simulator":[124,162],"environments":[125],"different":[127],"levels":[128],"fidelity,":[130],"parameterized":[133],"via":[134],"data.":[136],"Within":[137],"framework,":[139],"large":[141],"amount":[142],"randomized":[144],"experience":[145],"generated":[147],"low-fidelity":[150],"simulator,":[151],"whereupon":[152],"learned":[154],"skills":[155],"validated":[157],"regularly":[158],"high-fidelity":[161],"avoid":[164],"overfitting.":[165],"Finally,":[166],"phase,":[170],"agent":[172],"examined":[174],"concerning":[175],"safety":[176],"decision-making.":[179],"Extensive":[180],"evaluations":[184],"show":[185],"superiority":[187],"proposed":[190],"approach.":[191],"To":[192],"best":[194],"authors\u2019":[197],"knowledge,":[198],"this":[199],"first":[202],"application":[203],"lane-changing":[206],"policy":[207],"world.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}