{"id":"https://openalex.org/W4389666640","doi":"https://doi.org/10.1109/iros55552.2023.10341449","title":"Accelerating Reinforcement Learning for Autonomous Driving Using Task-Agnostic and Ego-Centric Motion Skills","display_name":"Accelerating Reinforcement Learning for Autonomous Driving Using Task-Agnostic and Ego-Centric Motion Skills","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389666640","doi":"https://doi.org/10.1109/iros55552.2023.10341449"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10341449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5101777618","display_name":"Tong Zhou","orcid":"https://orcid.org/0000-0002-8645-5246"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tong Zhou","raw_affiliation_strings":["SenseTime Research,Beijing,China","Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China","SenseTime Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SenseTime Research,Beijing,China","institution_ids":["https://openalex.org/I4210128910"]},{"raw_affiliation_string":"Department of Electronic Engineering, The Chinese University of Hong Kong, Shatin, N.T., Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101709753","display_name":"Letian Wang","orcid":"https://orcid.org/0000-0003-4433-2966"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Letian Wang","raw_affiliation_strings":["University of Toronto,Toronto,ON,CA","University of Toronto, Toronto, ON, CA"],"affiliations":[{"raw_affiliation_string":"University of Toronto,Toronto,ON,CA","institution_ids":[]},{"raw_affiliation_string":"University of Toronto, Toronto, ON, CA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044871071","display_name":"Ruobing Chen","orcid":"https://orcid.org/0000-0002-4660-0883"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruobing Chen","raw_affiliation_strings":["SenseTime Research,Beijing,China","SenseTime Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SenseTime Research,Beijing,China","institution_ids":["https://openalex.org/I4210128910"]},{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055099598","display_name":"Wenshuo Wang","orcid":"https://orcid.org/0000-0002-1860-8351"},"institutions":[{"id":"https://openalex.org/I1304598786","display_name":"Program for Appropriate Technology in Health","ror":"https://ror.org/02ycvrx49","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1304598786"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenshuo Wang","raw_affiliation_strings":["California PATH,UC Berkeley,CA,USA","California PATH, UC Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"California PATH,UC Berkeley,CA,USA","institution_ids":["https://openalex.org/I1304598786","https://openalex.org/I95457486"]},{"raw_affiliation_string":"California PATH, UC Berkeley, CA, USA","institution_ids":["https://openalex.org/I1304598786","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100345672","display_name":"Yu Liu","orcid":"https://orcid.org/0000-0001-9107-6390"},"institutions":[{"id":"https://openalex.org/I4210128910","display_name":"Group Sense (China)","ror":"https://ror.org/036wd5777","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210128910"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Liu","raw_affiliation_strings":["SenseTime Research,Beijing,China","SenseTime Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"SenseTime Research,Beijing,China","institution_ids":["https://openalex.org/I4210128910"]},{"raw_affiliation_string":"SenseTime Research, Beijing, China","institution_ids":["https://openalex.org/I4210128910"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101777618"],"corresponding_institution_ids":["https://openalex.org/I177725633","https://openalex.org/I4210128910"],"apc_list":null,"apc_paid":null,"fwci":2.6185,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.91963101,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"11289","last_page":"11296"},"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":0.9994000196456909,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9783999919891357,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7805266380310059},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7337159514427185},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7319600582122803},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6034241318702698},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.588789165019989},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5544890761375427},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5412696003913879},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4782261252403259},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4539778232574463},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4267321527004242},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3256005644798279},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07949799299240112}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7805266380310059},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7337159514427185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7319600582122803},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6034241318702698},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.588789165019989},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5544890761375427},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5412696003913879},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4782261252403259},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4539778232574463},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4267321527004242},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3256005644798279},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07949799299240112},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10341449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10341449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W2096785587","https://openalex.org/W2109910161","https://openalex.org/W2125612430","https://openalex.org/W2163411428","https://openalex.org/W2257979135","https://openalex.org/W2597350163","https://openalex.org/W2729615412","https://openalex.org/W2736601468","https://openalex.org/W2741122588","https://openalex.org/W2784715585","https://openalex.org/W2788862220","https://openalex.org/W2799151646","https://openalex.org/W2902592652","https://openalex.org/W2902711054","https://openalex.org/W2904246096","https://openalex.org/W2963099939","https://openalex.org/W2963438456","https://openalex.org/W2963713397","https://openalex.org/W2964227312","https://openalex.org/W2973183361","https://openalex.org/W2982316857","https://openalex.org/W3040033967","https://openalex.org/W3048659003","https://openalex.org/W3089952679","https://openalex.org/W3091516903","https://openalex.org/W3104946437","https://openalex.org/W3132530365","https://openalex.org/W3150384095","https://openalex.org/W3156047532","https://openalex.org/W3164631379","https://openalex.org/W3177774209","https://openalex.org/W3181452220","https://openalex.org/W3203076355","https://openalex.org/W3206540493","https://openalex.org/W3209949248","https://openalex.org/W3216786669","https://openalex.org/W4225997321","https://openalex.org/W4286891527","https://openalex.org/W6741002519","https://openalex.org/W6741010574","https://openalex.org/W6742461812","https://openalex.org/W6747473740","https://openalex.org/W6748603076","https://openalex.org/W6750186571","https://openalex.org/W6756675569","https://openalex.org/W6757043833","https://openalex.org/W6757592117","https://openalex.org/W6760439459","https://openalex.org/W6771989576","https://openalex.org/W6776440328","https://openalex.org/W6784712800","https://openalex.org/W6797717759","https://openalex.org/W6802864926","https://openalex.org/W6804238973","https://openalex.org/W6811084544"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2732813147","https://openalex.org/W2143460112","https://openalex.org/W3196817267"],"abstract_inverted_index":{"Efficient":[0],"and":[1,60,98,117,177],"effective":[2],"exploration":[3,156],"in":[4,11,63,109,123,135,151,159,174],"continuous":[5],"space":[6,67,72],"is":[7,129],"a":[8,70,93,115,124,146],"central":[9],"problem":[10],"applying":[12],"reinforcement":[13],"learning":[14,175],"(RL)":[15],"to":[16,41,43,51,132],"autonomous":[17],"driving.":[18],"Skills":[19],"learned":[20],"from":[21],"expert":[22],"demonstrations":[23,56],"or":[24,39],"designed":[25],"for":[26],"specific":[27],"tasks":[28,54],"can":[29,49,105,154],"benefit":[30],"the":[31,64,78],"exploration,":[32],"but":[33],"they":[34],"are":[35,142],"usually":[36],"costly-collected,":[37],"unbalanced/suboptimal,":[38],"failing":[40],"transfer":[42],"diverse":[44,110,130],"tasks.":[45,111,138],"However,":[46],"human":[47],"drivers":[48],"adapt":[50],"varied":[52],"driving":[53,162],"without":[55],"by":[57,77],"taking":[58],"efficient":[59],"structural":[61],"explorations":[62],"entire":[65],"skill":[66,121,149],"rather":[68],"than":[69],"limited":[71,94],"with":[73],"task-specific":[74,97],"skills.":[75,100],"Inspired":[76],"above":[79],"fact,":[80],"we":[81,113],"propose":[82],"an":[83],"RL":[84,153],"algorithm":[85],"exploring":[86],"all":[87],"feasible":[88],"motion":[89,120,126,140],"skills":[90,141],"instead":[91],"of":[92,96],"set":[95],"object-centric":[99],"Without":[101],"demonstrations,":[102],"our":[103,166],"method":[104],"still":[106],"perform":[107],"well":[108],"First,":[112],"build":[114],"task-agnostic":[116],"ego-centric":[118],"(TaEc)":[119],"library":[122],"pure":[125],"perspective,":[127],"which":[128,152],"enough":[131],"be":[133],"reusable":[134],"different":[136],"complex":[137],"The":[139],"then":[143],"encoded":[144],"into":[145],"low-dimension":[147],"latent":[148],"space,":[150],"do":[155],"efficiently.":[157],"Validations":[158],"various":[160],"challenging":[161],"scenarios":[163],"demonstrate":[164],"that":[165],"proposed":[167],"method,":[168],"TaEc-RL,":[169],"outperforms":[170],"its":[171],"counterparts":[172],"significantly":[173],"efficiency":[176],"task":[178],"performance.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}