{"id":"https://openalex.org/W3199922428","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533604","title":"Columba: A New Approach to Train an Agent for Autonomous Driving","display_name":"Columba: A New Approach to Train an Agent for Autonomous Driving","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3199922428","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533604","mag":"3199922428"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5009039982","display_name":"Ruiyang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruiyang Yang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences University of Chinese Academy of Sciences, State Key Laboratory of Computer Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences University of Chinese Academy of Sciences, State Key Laboratory of Computer Science, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109377270","display_name":"Hongyin Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyin Tang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences University of Chinese Academy of Sciences, State Key Laboratory of Computer Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences University of Chinese Academy of Sciences, State Key Laboratory of Computer Science, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621776","display_name":"Beihong Jin","orcid":"https://orcid.org/0000-0003-3683-4034"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beihong Jin","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences University of Chinese Academy of Sciences, State Key Laboratory of Computer Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences University of Chinese Academy of Sciences, State Key Laboratory of Computer Science, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072467335","display_name":"Kunchi Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kunchi Liu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences University of Chinese Academy of Sciences, State Key Laboratory of Computer Science, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences University of Chinese Academy of Sciences, State Key Laboratory of Computer Science, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009039982"],"corresponding_institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.12984361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9990000128746033,"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":0.9670000076293945,"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":0.757777214050293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6929874420166016},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.666201651096344},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6359177827835083},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.629636287689209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6036076545715332},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.5938793420791626},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5275672674179077},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4493168890476227}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.757777214050293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6929874420166016},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.666201651096344},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6359177827835083},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.629636287689209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6036076545715332},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5938793420791626},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5275672674179077},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4493168890476227},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533604","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1931877416","https://openalex.org/W2099471712","https://openalex.org/W2136922672","https://openalex.org/W2145339207","https://openalex.org/W2342840547","https://openalex.org/W2583993537","https://openalex.org/W2604382266","https://openalex.org/W2727840223","https://openalex.org/W2770884134","https://openalex.org/W2801811058","https://openalex.org/W2897522585","https://openalex.org/W2900788315","https://openalex.org/W2945023859","https://openalex.org/W2950102663","https://openalex.org/W2962957031","https://openalex.org/W2963277051","https://openalex.org/W2963328631","https://openalex.org/W2963587896","https://openalex.org/W2963864421","https://openalex.org/W2964067469","https://openalex.org/W2964201867","https://openalex.org/W2971116204","https://openalex.org/W2981207549","https://openalex.org/W3100944043","https://openalex.org/W3127561923","https://openalex.org/W3133456577","https://openalex.org/W4320013936","https://openalex.org/W6640174482","https://openalex.org/W6684921986","https://openalex.org/W6704559304","https://openalex.org/W6718092244","https://openalex.org/W6732249622","https://openalex.org/W6746462176","https://openalex.org/W6751399463","https://openalex.org/W6756303580","https://openalex.org/W6762387550","https://openalex.org/W6773319185","https://openalex.org/W6791332694"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W4293202849"],"abstract_inverted_index":{"For":[0],"autonomous":[1],"driving":[2,32],"in":[3,164],"extremely":[4],"complex":[5],"scenarios,":[6,33],"existing":[7,34],"research":[8],"utilizes":[9],"deep":[10,166],"reinforcement":[11,167],"learning":[12,15,51,168],"or":[13,44,100],"imitation":[14,171],"to":[16,25,68,96],"obtain":[17],"the":[18,26,41,50,66,98,104,108,115,120,122,127,130,139,147,153,165,170],"decision-making":[19],"capability":[20],"of":[21,30,79,103,110,132],"agents.":[22],"However,":[23],"due":[24],"incomplete":[27],"information":[28],"nature":[29],"such":[31,39],"techniques":[35],"usually":[36],"suffer":[37],"issues":[38],"as":[40],"incorrect":[42],"rewards":[43,116],"unstable":[45],"training":[46],"which":[47,64,160],"would":[48],"impact":[49],"quality":[52],"seriously.":[53],"In":[54,86],"this":[55],"paper,":[56],"we":[57],"propose":[58],"a":[59,90],"new":[60],"approach":[61],"named":[62],"Columba":[63,88,113,151],"trains":[65],"agent":[67,106,148],"learn":[69],"from":[70],"expert":[71],"trajectory":[72,76],"data":[73,77],"and":[74,92,126,158,169],"abnormal":[75],"instead":[78],"relying":[80],"on":[81,138],"any":[82],"manually-set":[83],"reward":[84],"functions.":[85],"particular,":[87],"designs":[89],"positive":[91],"negative":[93],"feedback":[94],"regulator":[95],"reduce":[97],"dangerous":[99],"bad":[101],"states":[102],"car":[105],"at":[107],"beginning":[109],"training.":[111],"Further,":[112],"generates":[114],"by":[117,150,156],"coordinating":[118],"with":[119],"discriminator,":[121],"random":[123],"distillation":[124],"network":[125],"regulator,":[128],"enhancing":[129],"accuracy":[131],"rewards.":[133],"We":[134],"conduct":[135],"extensive":[136],"experiments":[137],"Torcs":[140],"simulation":[141],"platform.":[142],"Experimental":[143],"results":[144],"show":[145],"that":[146],"trained":[149,155],"outperforms":[152],"agents":[154],"DDPG":[157],"GAIL,":[159],"are":[161],"strong":[162],"baselines":[163],"learning,":[172],"respectively.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}