{"id":"https://openalex.org/W4398249695","doi":"https://doi.org/10.1109/tits.2024.3400224","title":"Unsupervised Reinforcement Learning for Multi-Task Autonomous Driving: Expanding Skills and Cultivating Curiosity","display_name":"Unsupervised Reinforcement Learning for Multi-Task Autonomous Driving: Expanding Skills and Cultivating Curiosity","publication_year":2024,"publication_date":"2024-05-23","ids":{"openalex":"https://openalex.org/W4398249695","doi":"https://doi.org/10.1109/tits.2024.3400224"},"language":"en","primary_location":{"id":"doi:10.1109/tits.2024.3400224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3400224","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/A5104221352","display_name":"Zhenyu Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenyu Ma","raw_affiliation_strings":["School of Automotive Studies, Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100395654","display_name":"Xinyi Liu","orcid":"https://orcid.org/0000-0001-6411-8612"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyi Liu","raw_affiliation_strings":["School of Automotive Studies, Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003126186","display_name":"Yanjun Huang","orcid":"https://orcid.org/0000-0003-3133-8031"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanjun Huang","raw_affiliation_strings":["School of Automotive Studies, Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3133-8031","affiliations":[{"raw_affiliation_string":"School of Automotive Studies, Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":null,"apc_paid":null,"fwci":1.3133,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78561401,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"25","issue":"10","first_page":"14209","last_page":"14219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.9107999801635742,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.9107999801635742,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.8608014583587646},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6753134727478027},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6606249809265137},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5016682147979736},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.439886212348938},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.4214699864387512},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.39875736832618713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3726869225502014},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.2500947117805481},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.15771418809890747},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.10509583353996277}],"concepts":[{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8608014583587646},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6753134727478027},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6606249809265137},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5016682147979736},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.439886212348938},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4214699864387512},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.39875736832618713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3726869225502014},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2500947117805481},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.15771418809890747},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.10509583353996277}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tits.2024.3400224","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tits.2024.3400224","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":[],"awards":[{"id":"https://openalex.org/G5838297260","display_name":null,"funder_award_id":"U23B2061","funder_id":"https://openalex.org/F4320333688","funder_display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320333688","display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W2010130628","https://openalex.org/W2122508508","https://openalex.org/W2181724605","https://openalex.org/W2322020277","https://openalex.org/W2556477470","https://openalex.org/W2891076394","https://openalex.org/W2952194250","https://openalex.org/W2962762260","https://openalex.org/W2963168538","https://openalex.org/W2963438456","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964067469","https://openalex.org/W2979766322","https://openalex.org/W2995830828","https://openalex.org/W3080934299","https://openalex.org/W3127561923","https://openalex.org/W3132147085","https://openalex.org/W3174295900","https://openalex.org/W3186672455","https://openalex.org/W3201094358","https://openalex.org/W4221143263","https://openalex.org/W4225304231","https://openalex.org/W4225850546","https://openalex.org/W4226141644","https://openalex.org/W4226239849","https://openalex.org/W4283795252","https://openalex.org/W4286891004","https://openalex.org/W4312108280","https://openalex.org/W4320830001","https://openalex.org/W4383112908","https://openalex.org/W4386412395","https://openalex.org/W6684921986","https://openalex.org/W6730153900","https://openalex.org/W6748603076","https://openalex.org/W6756303580","https://openalex.org/W6771876938","https://openalex.org/W6780562256","https://openalex.org/W6791000347","https://openalex.org/W6791110673","https://openalex.org/W6799458897","https://openalex.org/W6803067813","https://openalex.org/W6810111970","https://openalex.org/W6810488170","https://openalex.org/W6843033949","https://openalex.org/W6847833339","https://openalex.org/W6849750003"],"related_works":["https://openalex.org/W3094054656","https://openalex.org/W4285676344","https://openalex.org/W2123270665","https://openalex.org/W4382584175","https://openalex.org/W2060310955","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W3196817267","https://openalex.org/W4211075255"],"abstract_inverted_index":{"In":[0,107],"recent":[1],"years,":[2],"reinforcement":[3,34],"learning":[4,209,229],"(RL)":[5],"has":[6],"been":[7],"widely":[8],"used":[9,117],"in":[10,25,92,125,145,193,206,213,244],"decision-making.":[11],"However,":[12],"it":[13,18,186,224],"still":[14,225],"faces":[15],"challenges":[16],"when":[17],"is":[19,130],"applied":[20],"to":[21,43,56,85,121,178,190,203,221],"autonomous":[22],"driving,":[23],"especially":[24],"complex":[26,214],"multi-task":[27,58,109,175],"scenarios.":[28],"This":[29,94,231],"paper":[30],"introduces":[31],"an":[32,37,227,234],"unsupervised":[33],"learning(URL),":[35],"called":[36],"improved":[38],"Contrastive":[39],"Intrinsic":[40],"Control":[41],"(CIC),":[42],"address":[44],"this":[45],"problem.":[46],"CIC":[47],"generates":[48],"skills":[49,62,115],"as":[50,63,78,118,156],"transferable":[51],"factors":[52],"between":[53,74],"different":[54,151],"tasks":[55,159],"enable":[57],"expansion.":[59],"By":[60],"comparing":[61],"potential":[64],"state":[65,69],"transfers":[66],"with":[67],"real":[68],"transfers,":[70],"the":[71,75,79,83,87,96,102,108,112,168,172,179,197,207,245],"mutual":[72],"information":[73],"two":[76],"serves":[77],"curiosity":[80,238],"that":[81,167],"drives":[82],"agents":[84],"explore":[86],"environment":[88],"and":[89,101,200,240],"gather":[90],"experience":[91],"advance.":[93],"helps":[95],"collection":[97],"of":[98,104,174,237],"valuable":[99],"experiences":[100],"acquisition":[103],"effective":[105,235],"skills.":[106],"expansion":[110],"phase,":[111],"unified":[113],"training":[114,129,137],"are":[116,143,154],"a":[119,146,188,201],"prior":[120],"enabling":[122],"rapid":[123],"convergence":[124,194],"various":[126],"environments.":[127],"Unified":[128],"performed":[131],"without":[132],"rewards,":[133],"followed":[134],"by":[135],"repeated":[136],"on":[138],"multiple":[139],"downstream":[140],"tasks.":[141],"Experiments":[142],"conducted":[144],"highway":[147],"environment,":[148],"where":[149,216],"three":[150],"driving":[152],"modes":[153],"differentiated":[155],"separate":[157],"RL":[158,218,241],"through":[160],"reward":[161],"functions.":[162],"The":[163],"experimental":[164],"results":[165],"demonstrate":[166],"proposed":[169],"method":[170],"possesses":[171],"ability":[173],"learning.":[176],"Compared":[177],"Deep":[180],"Deterministic":[181],"Policy":[182],"Gradient":[183],"(DDPG)":[184],"baseline,":[185],"achieves":[187,226],"30%":[189],"50%":[191],"improvement":[192,205],"speed":[195],"at":[196],"single-task":[198],"level":[199],"20%":[202],"40%":[204],"final":[208],"performance.":[210],"Furthermore,":[211],"even":[212],"tasks,":[215],"other":[217],"methods":[219],"struggle":[220],"learn":[222],"effectively,":[223],"obvious":[228],"ability.":[230],"approach":[232],"realizes":[233],"combination":[236],"mechanism,":[239],"decision":[242],"making":[243],"multitasking":[246],"domain.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}