{"id":"https://openalex.org/W3207654079","doi":"https://doi.org/10.1109/tnnls.2021.3116063","title":"Deep Reinforcement Learning on Autonomous Driving Policy With Auxiliary Critic Network","display_name":"Deep Reinforcement Learning on Autonomous Driving Policy With Auxiliary Critic Network","publication_year":2021,"publication_date":"2021-10-20","ids":{"openalex":"https://openalex.org/W3207654079","doi":"https://doi.org/10.1109/tnnls.2021.3116063","mag":"3207654079","pmid":"https://pubmed.ncbi.nlm.nih.gov/34669579"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3116063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3116063","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5068488260","display_name":"Yuanqing Wu","orcid":"https://orcid.org/0000-0001-9509-2670"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanqing Wu","raw_affiliation_strings":["School of Automation, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9509-2670","affiliations":[{"raw_affiliation_string":"School of Automation, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082970543","display_name":"Siqin Liao","orcid":"https://orcid.org/0009-0008-5623-059X"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siqin Liao","raw_affiliation_strings":["School of Automation, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668156","display_name":"Xiang Liu","orcid":"https://orcid.org/0000-0002-4874-4071"},"institutions":[{"id":"https://openalex.org/I2799850029","display_name":"Dongguan University of Technology","ror":"https://ror.org/01m8p7q42","country_code":"CN","type":"education","lineage":["https://openalex.org/I2799850029"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Liu","raw_affiliation_strings":["Dongguan University of Technology, Dongguan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dongguan University of Technology, Dongguan, China","institution_ids":["https://openalex.org/I2799850029"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101804803","display_name":"Zhihang Li","orcid":"https://orcid.org/0000-0002-9305-7924"},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhihang Li","raw_affiliation_strings":["School of Automation, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069617479","display_name":"Renquan Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I139024713","display_name":"Guangdong University of Technology","ror":"https://ror.org/04azbjn80","country_code":"CN","type":"education","lineage":["https://openalex.org/I139024713"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Renquan Lu","raw_affiliation_strings":["School of Automation, Guangdong University of Technology, Guangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Guangdong University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I139024713"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.0171,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.96873341,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"34","issue":"7","first_page":"3680","last_page":"3690"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9934999942779541,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9835000038146973,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/overtaking","display_name":"Overtaking","score":0.8724651336669922},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8540838956832886},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7312113642692566},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.674736738204956},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5931854248046875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5781462788581848},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.5543057918548584},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4819719195365906},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.4380784332752228},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4379803240299225},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.348397433757782},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.3287583589553833},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1518082320690155}],"concepts":[{"id":"https://openalex.org/C2778448659","wikidata":"https://www.wikidata.org/wiki/Q1931051","display_name":"Overtaking","level":2,"score":0.8724651336669922},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8540838956832886},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312113642692566},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.674736738204956},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5931854248046875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5781462788581848},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.5543057918548584},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4819719195365906},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.4380784332752228},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4379803240299225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.348397433757782},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.3287583589553833},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1518082320690155},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C147176958","wikidata":"https://www.wikidata.org/wiki/Q77590","display_name":"Civil engineering","level":1,"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":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057766","descriptor_name":"Policy","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3116063","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3116063","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34669579","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34669579","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G3492749694","display_name":null,"funder_award_id":"61922026","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6351919727","display_name":null,"funder_award_id":"62033003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6781961755","display_name":null,"funder_award_id":"2017B010116006","funder_id":"https://openalex.org/F4320335795","funder_display_name":"Science and Technology Planning Project of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335795","display_name":"Science and Technology Planning Project of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1574474448","https://openalex.org/W1771410628","https://openalex.org/W1988098565","https://openalex.org/W2046376809","https://openalex.org/W2076337359","https://openalex.org/W2119112357","https://openalex.org/W2139137304","https://openalex.org/W2167224731","https://openalex.org/W2583993537","https://openalex.org/W2727840223","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2787938642","https://openalex.org/W2897827648","https://openalex.org/W2963523627","https://openalex.org/W2963679616","https://openalex.org/W2963864421","https://openalex.org/W2964067469","https://openalex.org/W3009523569","https://openalex.org/W3017827511","https://openalex.org/W3100944043","https://openalex.org/W3110781789","https://openalex.org/W3153964553","https://openalex.org/W4214717370","https://openalex.org/W4237591687","https://openalex.org/W4298857966","https://openalex.org/W6634423325","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6684338915","https://openalex.org/W6684921986","https://openalex.org/W6741002519","https://openalex.org/W6748839928","https://openalex.org/W6756303580","https://openalex.org/W6774476237"],"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":{"Deep":[0],"reinforcement":[1],"learning":[2,7,59],"(DRL)":[3],"is":[4,64,121],"a":[5,30,47,76],"machine":[6],"method":[8,60,78,140,170],"based":[9,61],"on":[10,62,110,141],"rewards,":[11],"which":[12,98,120],"can":[13,171],"be":[14],"extended":[15],"to":[16,27,84,90,94,132],"solve":[17],"some":[18],"complex":[19,33],"and":[20,34,115,146,158,176],"realistic":[21],"decision-making":[22],"problems.":[23],"Autonomous":[24],"driving":[25,45,57,156,180],"needs":[26],"deal":[28],"with":[29,160],"variety":[31],"of":[32,41,69,102],"changeable":[35],"traffic":[36],"scenarios,":[37],"so":[38],"the":[39,67,92,100,111,117,124,129,134,142,150,173],"application":[40,49],"DRL":[42,63,162],"in":[43,149,179],"autonomous":[44,56],"presents":[46],"broad":[48],"prospect.":[50],"In":[51],"this":[52],"article,":[53],"an":[54,86,106],"end-to-end":[55],"policy":[58,71],"proposed.":[65],"On":[66],"basis":[68],"proximal":[70],"optimization":[72],"(PPO),":[73],"we":[74],"combine":[75],"curiosity-driven":[77],"called":[79],"recurrent":[80],"neural":[81],"network":[82,109,127,130],"(RNN)":[83],"generate":[85],"intrinsic":[87],"reward":[88],"signal":[89],"encounter":[91],"agent":[93],"explore":[95],"its":[96],"environment,":[97],"improves":[99],"efficiency":[101,175],"exploration.":[103],"We":[104,137],"introduce":[105],"auxiliary":[107],"critic":[108,126],"original":[112],"actor-critic":[113],"framework":[114],"choose":[116],"lower":[118],"estimate":[119],"predicted":[122],"by":[123],"dual":[125],"when":[128],"update":[131],"avoid":[133],"overestimation":[135],"bias.":[136],"test":[138],"our":[139,168],"lane-":[143],"keeping":[144],"task":[145,148],"overtaking":[147],"open":[151],"racing":[152],"car":[153],"simulator":[154,157],"(TORCS)":[155],"compare":[159],"other":[161],"methods,":[163],"experimental":[164],"results":[165],"show":[166],"that":[167],"proposed":[169],"improve":[172],"training":[174],"control":[177],"performance":[178],"tasks.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":28},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}