{"id":"https://openalex.org/W3206390859","doi":"https://doi.org/10.1109/mra.2021.3115980","title":"Prioritized Experience Replay-Based Deep Q Learning: Multiple-Reward Architecture for Highway Driving Decision Making","display_name":"Prioritized Experience Replay-Based Deep Q Learning: Multiple-Reward Architecture for Highway Driving Decision Making","publication_year":2021,"publication_date":"2021-10-19","ids":{"openalex":"https://openalex.org/W3206390859","doi":"https://doi.org/10.1109/mra.2021.3115980","mag":"3206390859"},"language":"en","primary_location":{"id":"doi:10.1109/mra.2021.3115980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mra.2021.3115980","pdf_url":null,"source":{"id":"https://openalex.org/S132261465","display_name":"IEEE Robotics & Automation Magazine","issn_l":"1070-9932","issn":["1070-9932","1558-223X"],"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 Robotics & Automation Magazine","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/A5081650208","display_name":"Wei Yuan","orcid":"https://orcid.org/0000-0003-4880-844X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wei Yuan","raw_affiliation_strings":["University of Michigan\u2013Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan\u2013Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120313132","display_name":"Yueyuan Li","orcid":"https://orcid.org/0009-0000-2822-1663"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueyuan Li","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078656916","display_name":"Hanyang Zhuang","orcid":"https://orcid.org/0000-0001-6668-9523"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hanyang Zhuang","raw_affiliation_strings":["University of Michigan\u2013Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Michigan\u2013Shanghai Jiao Tong University Joint Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"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/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunxiang Wang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009256880","display_name":"Ming Yang","orcid":"https://orcid.org/0000-0002-8679-9137"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Yang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Key Laboratory of System Control and Information Processing, Ministry of Education of China, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5081650208"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":3.9179,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.93461043,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"28","issue":"4","first_page":"21","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9916999936103821,"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"}},"topics":[{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9916999936103821,"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/T11373","display_name":"Sleep and Work-Related Fatigue","score":0.9771000146865845,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/T10042","display_name":"Neural and Behavioral Psychology Studies","score":0.9641000032424927,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overtaking","display_name":"Overtaking","score":0.8964959383010864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7572884559631348},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6039863228797913},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.5218557119369507},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5193682312965393},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5145649313926697},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5052679181098938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5052292943000793},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5004856586456299},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.46877163648605347},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.41100212931632996},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3847660720348358},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12367576360702515},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10739827156066895},{"id":"https://openalex.org/keywords/transport-engineering","display_name":"Transport engineering","score":0.09806501865386963},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08231344819068909}],"concepts":[{"id":"https://openalex.org/C2778448659","wikidata":"https://www.wikidata.org/wiki/Q1931051","display_name":"Overtaking","level":2,"score":0.8964959383010864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7572884559631348},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6039863228797913},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.5218557119369507},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5193682312965393},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5145649313926697},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5052679181098938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5052292943000793},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5004856586456299},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.46877163648605347},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.41100212931632996},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3847660720348358},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12367576360702515},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10739827156066895},{"id":"https://openalex.org/C22212356","wikidata":"https://www.wikidata.org/wiki/Q775325","display_name":"Transport engineering","level":1,"score":0.09806501865386963},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08231344819068909},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mra.2021.3115980","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mra.2021.3115980","pdf_url":null,"source":{"id":"https://openalex.org/S132261465","display_name":"IEEE Robotics & Automation Magazine","issn_l":"1070-9932","issn":["1070-9932","1558-223X"],"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 Robotics & Automation Magazine","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7400000095367432,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2297757108","display_name":null,"funder_award_id":"U1764264","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2591868390","display_name":null,"funder_award_id":"61873165","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3994246717","display_name":null,"funder_award_id":"62173228","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1557517019","https://openalex.org/W1836583613","https://openalex.org/W1863227302","https://openalex.org/W1900041959","https://openalex.org/W2017372880","https://openalex.org/W2023122515","https://openalex.org/W2057587543","https://openalex.org/W2126288068","https://openalex.org/W2132622533","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2201581102","https://openalex.org/W2342840547","https://openalex.org/W2559767995","https://openalex.org/W2563338958","https://openalex.org/W2583993537","https://openalex.org/W2624731731","https://openalex.org/W2746553466","https://openalex.org/W2890375627","https://openalex.org/W2897827648","https://openalex.org/W2950892788","https://openalex.org/W2951799221","https://openalex.org/W2963322416","https://openalex.org/W2963864421","https://openalex.org/W2991137823","https://openalex.org/W3100247915","https://openalex.org/W3100944043","https://openalex.org/W3119981760","https://openalex.org/W4298857966","https://openalex.org/W6616173779","https://openalex.org/W6679365036"],"related_works":["https://openalex.org/W4328006269","https://openalex.org/W2242368318","https://openalex.org/W2041225042","https://openalex.org/W2742847962","https://openalex.org/W2962918551","https://openalex.org/W2972522277","https://openalex.org/W4288110829","https://openalex.org/W4319083788","https://openalex.org/W3022038857","https://openalex.org/W2734912394"],"abstract_inverted_index":{"Decision":[0],"making":[1],"is":[2,20,107,127,153],"a":[3,78,83,90,123],"fundamental":[4],"component":[5],"to":[6,48,66,155],"ensure":[7],"safe":[8],"autonomous":[9],"driving":[10,96,161],"in":[11],"highway":[12,95],"scenarios.":[13],"The":[14],"mainstream":[15],"architecture":[16,92],"for":[17,56,94],"this":[18,75],"task":[19],"the":[21,35,45,59,64,102,110,113,147,156],"classical":[22],"deep":[23],"Q":[24,114,117],"learning":[25,67],"network":[26],"(DQN).":[27],"However,":[28],"there":[29],"remain":[30],"two":[31],"major":[32],"issues":[33],"with":[34,89,109,159],"DQN:":[36],"1)":[37],"because":[38],"of":[39,104],"its":[40],"traditional":[41,157],"experience":[42,85],"replay":[43,86],"mechanism,":[44],"model":[46,65,80],"tends":[47],"learn":[49],"bias":[50],"from":[51],"imbalanced":[52],"data,":[53],"and":[54,116,140,166],"2)":[55],"multiobjective":[57],"tasks,":[58],"unitary":[60],"reward":[61,125],"function":[62,126],"limits":[63],"representative":[68],"domain":[69],"knowledge.":[70],"To":[71],"address":[72],"these":[73],"problems,":[74],"article":[76],"proposes":[77],"DQN":[79,152],"based":[81,133],"on":[82,134],"prioritized":[84,149],"(PER)":[87],"mechanism":[88],"multireward":[91],"(MRA)":[93],"decision":[97],"making.":[98],"For":[99,119],"balanced":[100],"training,":[101,122],"importance":[103],"memory":[105],"samples":[106],"encoded":[108],"error":[111],"between":[112],"estimation":[115],"target.":[118],"more":[120],"directional":[121],"single":[124],"decomposed":[128],"into":[129],"three":[130],"minor":[131],"ones":[132],"prior":[135],"knowledge,":[136],"emphasizing":[137],"speed,":[138],"overtaking,":[139],"lane":[141,164],"changing.":[142],"Experimental":[143],"results":[144],"indicate":[145],"that":[146],"proposed":[148],"MRA":[150],"(PMRA)":[151],"superior":[154],"DQN,":[158],"higher":[160],"speeds,":[162],"less":[163],"changing,":[165],"safer":[167],"overtaking.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}