{"id":"https://openalex.org/W3206880326","doi":"https://doi.org/10.1109/icra48506.2021.9561450","title":"Learning robust driving policies without online exploration","display_name":"Learning robust driving policies without online exploration","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3206880326","doi":"https://doi.org/10.1109/icra48506.2021.9561450","mag":"3206880326"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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/A5101753111","display_name":"Daniel Graves","orcid":"https://orcid.org/0000-0002-5345-6584"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Daniel Graves","raw_affiliation_strings":["Noah\u2019s Ark Lab, Huawei Technologies Canada","Noah's Ark Lab, Huawei Technologies Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046413911","display_name":"Nhat M. Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Nhat M. Nguyen","raw_affiliation_strings":["Noah\u2019s Ark Lab, Huawei Technologies Canada","Noah's Ark Lab, Huawei Technologies Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045443801","display_name":"Kimia Hassanzadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kimia Hassanzadeh","raw_affiliation_strings":["Noah\u2019s Ark Lab, Huawei Technologies Canada","Noah's Ark Lab, Huawei Technologies Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085327057","display_name":"Jun Jin","orcid":"https://orcid.org/0000-0002-4295-502X"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jun Jin","raw_affiliation_strings":["Noah\u2019s Ark Lab, Huawei Technologies Canada","Noah's Ark Lab, Huawei Technologies Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081222445","display_name":"Jun Luo","orcid":"https://orcid.org/0000-0002-7036-5158"},"institutions":[{"id":"https://openalex.org/I4210115038","display_name":"Huawei Technologies (Canada)","ror":"https://ror.org/026venb53","country_code":"CA","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210115038"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jun Luo","raw_affiliation_strings":["Noah\u2019s Ark Lab, Huawei Technologies Canada","Noah's Ark Lab, Huawei Technologies Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Noah\u2019s Ark Lab, Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]},{"raw_affiliation_string":"Noah's Ark Lab, Huawei Technologies Canada","institution_ids":["https://openalex.org/I4210115038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210115038"],"apc_list":null,"apc_paid":null,"fwci":0.093,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42452611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"48","issue":null,"first_page":"13186","last_page":"13193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9991000294685364,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9991000294685364,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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/T10524","display_name":"Traffic control and management","score":0.9815000295639038,"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":0.8715348243713379},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.7809657454490662},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7755106687545776},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.647513747215271},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6280338764190674},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6199679374694824},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.5057117938995361},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.48142120242118835},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.470912903547287},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4545714855194092},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.41385698318481445}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8715348243713379},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.7809657454490662},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7755106687545776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.647513747215271},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6280338764190674},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6199679374694824},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.5057117938995361},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.48142120242118835},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.470912903547287},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4545714855194092},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41385698318481445},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48506.2021.9561450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","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":91,"referenced_works":["https://openalex.org/W132157653","https://openalex.org/W1757796397","https://openalex.org/W1904406446","https://openalex.org/W1979317847","https://openalex.org/W2049842224","https://openalex.org/W2100677568","https://openalex.org/W2104228245","https://openalex.org/W2108086591","https://openalex.org/W2119112357","https://openalex.org/W2132622533","https://openalex.org/W2153791616","https://openalex.org/W2158282517","https://openalex.org/W2162489854","https://openalex.org/W2165150801","https://openalex.org/W2182631142","https://openalex.org/W2201581102","https://openalex.org/W2203345135","https://openalex.org/W2234130870","https://openalex.org/W2250461676","https://openalex.org/W2257979135","https://openalex.org/W2342840547","https://openalex.org/W2343568200","https://openalex.org/W2440926996","https://openalex.org/W2570416447","https://openalex.org/W2575705757","https://openalex.org/W2583993537","https://openalex.org/W2624731731","https://openalex.org/W2740067745","https://openalex.org/W2745467776","https://openalex.org/W2754517384","https://openalex.org/W2766127076","https://openalex.org/W2773834020","https://openalex.org/W2889923199","https://openalex.org/W2893662673","https://openalex.org/W2898155524","https://openalex.org/W2899652047","https://openalex.org/W2904453761","https://openalex.org/W2905173465","https://openalex.org/W2916826721","https://openalex.org/W2942608247","https://openalex.org/W2950347959","https://openalex.org/W2950872548","https://openalex.org/W2950892788","https://openalex.org/W2962717849","https://openalex.org/W2963477884","https://openalex.org/W2963704132","https://openalex.org/W2963858432","https://openalex.org/W2964068481","https://openalex.org/W2971092880","https://openalex.org/W2979211489","https://openalex.org/W2979863294","https://openalex.org/W2981030070","https://openalex.org/W2981992989","https://openalex.org/W3003329097","https://openalex.org/W3004186391","https://openalex.org/W3022566517","https://openalex.org/W3041202696","https://openalex.org/W3100397002","https://openalex.org/W3100944043","https://openalex.org/W3127561923","https://openalex.org/W4288333940","https://openalex.org/W4288363736","https://openalex.org/W4289303880","https://openalex.org/W4298101950","https://openalex.org/W4298857966","https://openalex.org/W4302570325","https://openalex.org/W6637967152","https://openalex.org/W6639845178","https://openalex.org/W6676062988","https://openalex.org/W6679365036","https://openalex.org/W6683084483","https://openalex.org/W6684205842","https://openalex.org/W6687681856","https://openalex.org/W6687803322","https://openalex.org/W6704084210","https://openalex.org/W6704559304","https://openalex.org/W6718190810","https://openalex.org/W6729556111","https://openalex.org/W6743448849","https://openalex.org/W6744123322","https://openalex.org/W6745122088","https://openalex.org/W6754629161","https://openalex.org/W6755653560","https://openalex.org/W6755904448","https://openalex.org/W6757469721","https://openalex.org/W6759370769","https://openalex.org/W6764793234","https://openalex.org/W6768617876","https://openalex.org/W6772963868","https://openalex.org/W6773319185","https://openalex.org/W6776438516"],"related_works":["https://openalex.org/W4225619808","https://openalex.org/W4400438570","https://openalex.org/W4221145086","https://openalex.org/W4376223516","https://openalex.org/W4226221094","https://openalex.org/W4226042081","https://openalex.org/W4388926065","https://openalex.org/W4387293922","https://openalex.org/W4388482290","https://openalex.org/W3207447243"],"abstract_inverted_index":{"We":[0,40],"propose":[1],"a":[2],"multi-time-scale":[3],"predictive":[4],"representation":[5,45],"learning":[6,46,57,101],"method":[7,47,78],"to":[8,21,62,71],"efficiently":[9,66],"learn":[10],"robust":[11],"driving":[12],"policies":[13],"in":[14,35,52,85,110],"an":[15,53],"offline":[16,37,54,84],"manner":[17],"that":[18,42,96],"generalize":[19,63],"well":[20,64],"novel":[22,68],"road":[23],"geometries,":[24],"and":[25,27,65,113,121],"damaged":[26],"distracting":[28],"lane":[29],"conditions":[30,69],"which":[31,88],"are":[32],"not":[33],"covered":[34],"the":[36,60,86,90,117],"training":[38,80],"data.":[39],"show":[41],"our":[43,124],"proposed":[44,77,125],"can":[48],"be":[49],"applied":[50],"easily":[51],"(batch)":[55],"reinforcement":[56,100],"setting":[58],"demonstrating":[59],"ability":[61],"under":[67],"compared":[70],"standard":[72],"batch":[73],"RL":[74],"methods.":[75],"Our":[76],"utilizes":[79],"data":[81],"collected":[82],"entirely":[83],"real-world":[87,103,114],"removes":[89],"need":[91],"of":[92,119,123],"intensive":[93],"online":[94],"explorations":[95],"impede":[97],"applying":[98],"deep":[99],"on":[102],"robot":[104],"training.":[105],"Various":[106],"experiments":[107],"were":[108],"conducted":[109],"both":[111],"simulator":[112],"scenarios":[115],"for":[116],"purpose":[118],"evaluation":[120],"analysis":[122],"claims.":[126]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}