{"id":"https://openalex.org/W3045839081","doi":"https://doi.org/10.23919/acc45564.2020.9147960","title":"Smooth Actor-Critic Algorithm for End-to-End Autonomous Driving","display_name":"Smooth Actor-Critic Algorithm for End-to-End Autonomous Driving","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3045839081","doi":"https://doi.org/10.23919/acc45564.2020.9147960","mag":"3045839081"},"language":"en","primary_location":{"id":"doi:10.23919/acc45564.2020.9147960","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5029808668","display_name":"Wenjie Song","orcid":"https://orcid.org/0000-0002-4121-908X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjie Song","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101889464","display_name":"Shixian Liu","orcid":"https://orcid.org/0000-0003-1768-7913"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shixian Liu","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100704698","display_name":"Yujun Li","orcid":"https://orcid.org/0000-0002-8701-5971"},"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":"Yujun Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062124960","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0003-3964-2433"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100299426","display_name":"Changle Xiang","orcid":"https://orcid.org/0009-0002-5424-1670"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changle Xiang","raw_affiliation_strings":["School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, Beijing Institute of Technology, Beijing, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3242","last_page":"3248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9869999885559082,"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":0.9836999773979187,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7606749534606934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.676240861415863},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5892630815505981},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5016272068023682},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39900773763656616},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34918588399887085},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.34539568424224854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29143381118774414},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1610979437828064},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.1467122733592987}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7606749534606934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.676240861415863},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5892630815505981},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5016272068023682},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39900773763656616},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34918588399887085},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.34539568424224854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29143381118774414},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1610979437828064},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1467122733592987},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc45564.2020.9147960","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc45564.2020.9147960","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1771410628","https://openalex.org/W2046376809","https://openalex.org/W2119112357","https://openalex.org/W2124267516","https://openalex.org/W2145339207","https://openalex.org/W2156737235","https://openalex.org/W2201581102","https://openalex.org/W2342662072","https://openalex.org/W2604173613","https://openalex.org/W2604883922","https://openalex.org/W2726989136","https://openalex.org/W2727840223","https://openalex.org/W2749928749","https://openalex.org/W2766447205","https://openalex.org/W2771506457","https://openalex.org/W2909906617","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W3100789280","https://openalex.org/W4205513846","https://openalex.org/W4298857966","https://openalex.org/W4394661925","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6683195989","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6692846177","https://openalex.org/W6704571135","https://openalex.org/W6735738130","https://openalex.org/W6743802245","https://openalex.org/W6746316224","https://openalex.org/W6756925679","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"For":[0],"the":[1,14,34,48,67,75,86,90,94,100,126],"intelligent":[2],"sequential":[3],"decision-making":[4],"tasks":[5],"like":[6],"autonomous":[7,43,142],"driving,":[8,44],"decisions":[9],"or":[10,26],"actions":[11,38,79,132],"made":[12],"by":[13],"agent":[15,35],"in":[16,80,112,119],"a":[17,61,81],"short":[18],"period":[19],"of":[20,70,89,114],"time":[21],"should":[22],"be":[23,109],"smooth":[24,37,49],"enough":[25],"not":[27],"too":[28],"choppy.":[29],"In":[30],"order":[31],"to":[32,66,73],"help":[33],"learn":[36],"(steering,":[39],"accelerating,":[40],"braking)":[41],"for":[42,52,99,138],"this":[45],"paper":[46],"proposes":[47],"actor-critic":[50],"algorithm":[51],"both":[53],"deterministic":[54],"policy":[55,58],"and":[56,97,133],"stochastic":[57],"systems.":[59],"Specifically,":[60],"regularization":[62],"term":[63],"is":[64],"added":[65],"objective":[68],"function":[69],"actorcritic":[71],"methods":[72,102,127],"constrain":[74],"difference":[76],"between":[77],"neighbouring":[78],"small":[82],"region":[83],"without":[84],"affecting":[85],"convergence":[87],"performance":[88,137],"whole":[91],"system.":[92],"Then,":[93],"theoretical":[95],"analysis":[96],"proof":[98],"modified":[101],"are":[103],"conducted":[104],"so":[105],"that":[106,125],"it":[107],"can":[108,128],"theoretically":[110],"guaranteed":[111],"terms":[113],"iterative":[115],"improvements.":[116],"Moreover,":[117],"experiments":[118],"different":[120],"simulation":[121],"systems":[122],"also":[123],"prove":[124],"generate":[129],"much":[130],"smoother":[131],"obtain":[134],"more":[135],"robust":[136],"reinforcement":[139],"learning-based":[140],"End-to-End":[141],"driving.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}