{"id":"https://openalex.org/W3200694950","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533791","title":"Online Virtual Training in Soft Actor-Critic for Autonomous Driving","display_name":"Online Virtual Training in Soft Actor-Critic for Autonomous Driving","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3200694950","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533791","mag":"3200694950"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533791","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/A5009578316","display_name":"Maryam Savari","orcid":"https://orcid.org/0000-0003-2439-0405"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Maryam Savari","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011352362","display_name":"Yoonsuck Choe","orcid":"https://orcid.org/0000-0002-1454-4610"},"institutions":[{"id":"https://openalex.org/I91045830","display_name":"Texas A&M University","ror":"https://ror.org/01f5ytq51","country_code":"US","type":"education","lineage":["https://openalex.org/I91045830"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoonsuck Choe","raw_affiliation_strings":["Texas A&M University, College Station, TX, USA"],"affiliations":[{"raw_affiliation_string":"Texas A&M University, College Station, TX, USA","institution_ids":["https://openalex.org/I91045830"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5009578316"],"corresponding_institution_ids":["https://openalex.org/I91045830"],"apc_list":null,"apc_paid":null,"fwci":0.4079,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.68987488,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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":0.9993000030517578,"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":0.9993000030517578,"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":0.996399998664856,"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":0.9876999855041504,"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":0.7281089425086975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.677790641784668},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6618669629096985},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5625348687171936},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4946291148662567},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49253663420677185},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.4798959493637085},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.419970840215683},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41937553882598877},{"id":"https://openalex.org/keywords/virtual-machine","display_name":"Virtual machine","score":0.4125010371208191},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37820473313331604},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.33608144521713257},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.29641154408454895},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.20530492067337036}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7281089425086975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.677790641784668},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6618669629096985},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5625348687171936},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4946291148662567},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49253663420677185},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.4798959493637085},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.419970840215683},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41937553882598877},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.4125010371208191},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37820473313331604},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.33608144521713257},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.29641154408454895},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.20530492067337036},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533791","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533791","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1575592356","https://openalex.org/W1599353299","https://openalex.org/W1771410628","https://openalex.org/W1968962398","https://openalex.org/W2156737235","https://openalex.org/W2173248099","https://openalex.org/W2556958149","https://openalex.org/W2583993537","https://openalex.org/W2781726626","https://openalex.org/W2785379783","https://openalex.org/W2786800733","https://openalex.org/W2793939502","https://openalex.org/W2837605352","https://openalex.org/W2897470356","https://openalex.org/W2904246096","https://openalex.org/W2908550123","https://openalex.org/W2948275977","https://openalex.org/W2950226226","https://openalex.org/W2963095800","https://openalex.org/W2963363446","https://openalex.org/W2963367680","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2968983352","https://openalex.org/W2977322142","https://openalex.org/W2977843878","https://openalex.org/W2978084855","https://openalex.org/W2997985982","https://openalex.org/W3009593063","https://openalex.org/W3091492359","https://openalex.org/W3100944043","https://openalex.org/W4302282707","https://openalex.org/W6634413486","https://openalex.org/W6638018090","https://openalex.org/W6683195989","https://openalex.org/W6684921986","https://openalex.org/W6692846177","https://openalex.org/W6730111887","https://openalex.org/W6747473740","https://openalex.org/W6748221089","https://openalex.org/W6748314335","https://openalex.org/W6757592117","https://openalex.org/W6763213874","https://openalex.org/W6768058739"],"related_works":["https://openalex.org/W4319083788","https://openalex.org/W3005560120","https://openalex.org/W3022038857","https://openalex.org/W2774891019","https://openalex.org/W4287626175","https://openalex.org/W2750116526","https://openalex.org/W4364383453","https://openalex.org/W1504101963","https://openalex.org/W3212784026","https://openalex.org/W837607586"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2,116,144],"(RL)":[3],"algorithms":[4,30,44,64],"are":[5,45],"widely":[6],"being":[7],"used":[8],"in":[9,22,65,90,164,168,174,184,192,219],"autonomous":[10,27,75,172,224],"driving":[11,76,89,173],"due":[12],"to":[13,16,32,37,40,79,120,150,207,216],"their":[14],"ability":[15],"cope":[17],"with":[18,47,115],"unseen":[19],"environments.":[20],"However,":[21],"a":[23,80,181,189],"complex":[24],"domain":[25],"like":[26],"driving,":[28],"these":[29,43],"need":[31],"explore":[33],"the":[34,48,87,91,102,106,127,131,175,185,208],"environment":[35],"enough":[36],"be":[38,217],"able":[39],"converge.":[41],"Therefore,":[42],"faced":[46],"problem":[49],"of":[50,57,104,130,140],"long":[51],"training":[52,107,128,186,202],"times":[53],"and":[54,143,162,171,188,199],"large":[55],"amounts":[56],"data.":[58],"In":[59,94],"addition,":[60],"using":[61],"deep":[62],"RL":[63],"areas":[66],"that":[67],"safety":[68,81],"is":[69,148,214],"an":[70,135,152,165],"important":[71],"factor":[72],"such":[73],"as":[74,205],"can":[77,125],"lead":[78],"issue":[82],"since":[83],"we":[84,97,110],"cannot":[85],"leave":[86],"car":[88],"street":[92],"unattended.":[93],"this":[95],"research,":[96],"tested":[98,163],"two":[99],"methods":[100],"for":[101,195,223],"purpose":[103],"reducing":[105],"time.":[108],"First,":[109],"pre-trained":[111],"Soft":[112],"Actor-Critic":[113],"(SAC)":[114],"from":[117,145],"Demonstrations":[118],"(LfD)":[119],"find":[121],"out":[122],"if":[123],"pre-training":[124],"reduce":[126],"time":[129,187],"SAC":[132],"algorithm.":[133],"Then,":[134],"online":[136],"end-to-end":[137],"combination":[138],"method":[139],"SAC,":[141],"LfD,":[142],"Interventions":[146],"(LfI)":[147],"proposed":[149,212],"train":[151],"agent":[153],"(dubbed":[154],"Online":[155,196,200],"Virtual":[156,201],"Training).":[157],"Both":[158],"scenarios":[159,222],"were":[160],"implemented":[161],"inverted-pendulum":[166],"task":[167],"OpenAI":[169],"gym":[170],"Carla":[176],"simulator.":[177],"The":[178,211],"results":[179],"showed":[180],"dramatic":[182],"reduction":[183],"significant":[190],"increase":[191],"gaining":[193],"rewards":[194],"LfD":[197],"(33%)":[198],"(36":[203],"%)":[204],"compare":[206],"baseline":[209],"SAC.":[210],"approach":[213],"expected":[215],"effective":[218],"daily":[220],"commute":[221],"driving.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}