{"id":"https://openalex.org/W2991137823","doi":"https://doi.org/10.1109/itsc.2019.8917304","title":"Multi-Reward Architecture based Reinforcement Learning for Highway Driving Policies","display_name":"Multi-Reward Architecture based Reinforcement Learning for Highway Driving Policies","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2991137823","doi":"https://doi.org/10.1109/itsc.2019.8917304","mag":"2991137823"},"language":"en","primary_location":{"id":"doi:10.1109/itsc.2019.8917304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc.2019.8917304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 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/A5081650208","display_name":"Wei Yuan","orcid":"https://orcid.org/0000-0003-4880-844X"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Yuan","raw_affiliation_strings":["Department of Automation, Ministry of Education of China, Shanghai, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Ministry of Education of China, Shanghai, CN","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009256880","display_name":"Ming Yang","orcid":"https://orcid.org/0000-0002-8679-9137"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yang","raw_affiliation_strings":["Department of Automation, Ministry of Education of China, Shanghai, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Ministry of Education of China, Shanghai, CN","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102910715","display_name":"Yuesheng He","orcid":"https://orcid.org/0000-0003-3063-4242"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuesheng He","raw_affiliation_strings":["Department of Automation, Ministry of Education of China, Shanghai, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Ministry of Education of China, Shanghai, CN","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048517656","display_name":"Chunxiang Wang","orcid":"https://orcid.org/0000-0002-6885-6740"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunxiang Wang","raw_affiliation_strings":["Department of Automation, Ministry of Education of China, Shanghai, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Ministry of Education of China, Shanghai, CN","institution_ids":["https://openalex.org/I1327237609"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040568223","display_name":"Bing Wang","orcid":"https://orcid.org/0000-0002-3314-3409"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"government","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bing Wang","raw_affiliation_strings":["Department of Automation, Ministry of Education of China, Shanghai, CN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Ministry of Education of China, Shanghai, CN","institution_ids":["https://openalex.org/I1327237609"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1327237609"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3810","last_page":"3815"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9976000189781189,"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":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.878962516784668},{"id":"https://openalex.org/keywords/overtaking","display_name":"Overtaking","score":0.7883898019790649},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6968263387680054},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.5062853097915649},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49213308095932007},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4587010145187378},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.45642703771591187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41901981830596924},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17232710123062134},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.15326616168022156},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.13445839285850525},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08486771583557129}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.878962516784668},{"id":"https://openalex.org/C2778448659","wikidata":"https://www.wikidata.org/wiki/Q1931051","display_name":"Overtaking","level":2,"score":0.7883898019790649},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6968263387680054},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.5062853097915649},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49213308095932007},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4587010145187378},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.45642703771591187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41901981830596924},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17232710123062134},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.15326616168022156},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.13445839285850525},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08486771583557129},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itsc.2019.8917304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itsc.2019.8917304","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Intelligent Transportation Systems Conference (ITSC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.5099999904632568}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1999874108","https://openalex.org/W2073384958","https://openalex.org/W2109910161","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2167224731","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2194775991","https://openalex.org/W2257979135","https://openalex.org/W2342840547","https://openalex.org/W2559767995","https://openalex.org/W2563338958","https://openalex.org/W2613718673","https://openalex.org/W2624731731","https://openalex.org/W2746553466","https://openalex.org/W2766447205","https://openalex.org/W2887286974","https://openalex.org/W2897827648","https://openalex.org/W2950892788","https://openalex.org/W2951799221","https://openalex.org/W2963864421","https://openalex.org/W4211221179","https://openalex.org/W6620707391","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6704559304","https://openalex.org/W6731187701"],"related_works":["https://openalex.org/W3084163143","https://openalex.org/W3198453306","https://openalex.org/W3081587374","https://openalex.org/W591161629","https://openalex.org/W2294880310","https://openalex.org/W2102544652","https://openalex.org/W3208192858","https://openalex.org/W2618142536","https://openalex.org/W4251855072","https://openalex.org/W1998625354"],"abstract_inverted_index":{"A":[0,70],"safe":[1],"and":[2,27,109,183,198,236],"efficient":[3,235],"driving":[4,15,50,68,84,181],"policy":[5],"is":[6,41,74,95,128,135,187,233],"essential":[7],"for":[8,19,48,66,79,90,103,107,112,122,148,238],"the":[9,23,30,87,92,101,105,110,145,149,158,162,179,184,191,196,199,206,212,239],"future":[10,240],"autonomous":[11,241],"highway":[12,49,67,180,242],"driving.":[13,243],"However,":[14],"policies":[16,51],"are":[17,171],"hard":[18],"modeling":[20],"because":[21],"of":[22,25,29,82,120,140,164,226,230],"diversity":[24],"scenes":[26],"uncertainties":[28],"interaction":[31],"with":[32,219],"surrounding":[33],"vehicles.":[34],"The":[35,126,154],"state-of-the-art":[36],"deep":[37],"reinforcement":[38,64],"learning":[39,65],"method":[40,208,214],"unable":[42],"to":[43,76,97,189],"learn":[44],"good":[45],"domain":[46,124],"knowledge":[47],"using":[52],"single":[53,71,216],"reward":[54,72,94,102,106,111,116,151,217],"architecture.":[55],"This":[56],"paper":[57],"proposes":[58],"a":[59,118,174],"Multi-Reward":[60],"Architecture":[61],"(MRA)":[62],"based":[63,160],"policies.":[69,85],"function":[73],"decomposed":[75,96],"multi-reward":[77],"functions":[78,152],"better":[80,210],"representation":[81],"multi-dimensional":[83],"Besides":[86],"big":[88],"penalty":[89],"collision,":[91],"overall":[93],"three":[98,138,168,220],"dimensional":[99],"rewards:":[100],"speed,":[104,223],"overtake,":[108],"lane-change.":[113],"Then,":[114],"each":[115],"trains":[117],"branch":[119],"Q-network":[121,127],"corresponding":[123,146],"knowledge.":[125],"divided":[129],"into":[130],"two":[131],"parts:":[132],"low-level":[133],"network":[134],"shared":[136],"by":[137],"branches":[139],"high-level":[141],"networks,":[142],"which":[143,177,232],"approximate":[144],"Q-value":[147],"different":[150],"respectively.":[153],"agent":[155,185],"car":[156,186],"chooses":[157],"action":[159],"on":[161,215],"sum":[163],"Q":[165],"vectors":[166],"from":[167],"branches.":[169],"Experiments":[170],"conducted":[172],"in":[173],"simulation":[175],"platform,":[176],"performs":[178,209],"process":[182],"able":[188],"provide":[190],"commonly":[192],"used":[193],"sensor":[194],"data:":[195],"image":[197],"point":[200],"cloud.":[201],"Experiment":[202],"results":[203],"show":[204],"that":[205],"proposed":[207],"than":[211],"DQN":[213],"architecture":[218],"evaluations:":[221],"higher":[222],"lower":[224],"frequency":[225],"lane-change,":[227],"more":[228,234],"quantity":[229],"overtaking,":[231],"safer":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}