{"id":"https://openalex.org/W3090307871","doi":"https://doi.org/10.1109/icra40945.2020.9197159","title":"Fast Adaptation of Deep Reinforcement Learning-Based Navigation Skills to Human Preference","display_name":"Fast Adaptation of Deep Reinforcement Learning-Based Navigation Skills to Human Preference","publication_year":2020,"publication_date":"2020-05-01","ids":{"openalex":"https://openalex.org/W3090307871","doi":"https://doi.org/10.1109/icra40945.2020.9197159","mag":"3090307871"},"language":"en","primary_location":{"id":"doi:10.1109/icra40945.2020.9197159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 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/A5102865709","display_name":"Jinyoung Choi","orcid":"https://orcid.org/0000-0002-2470-9722"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jinyoung Choi","raw_affiliation_strings":["NAVER LABS, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"NAVER LABS, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000827821","display_name":"Christopher R. Dance","orcid":"https://orcid.org/0009-0006-5355-9619"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christopher Dance","raw_affiliation_strings":["NAVER LABS Europe, Meylan, France"],"affiliations":[{"raw_affiliation_string":"NAVER LABS Europe, Meylan, France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100453002","display_name":"Jungeun Kim","orcid":"https://orcid.org/0009-0006-9757-7149"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jung-eun Kim","raw_affiliation_strings":["NAVER LABS, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"NAVER LABS, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112592913","display_name":"Kyung-Sik Park","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyung-sik Park","raw_affiliation_strings":["NAVER LABS, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"NAVER LABS, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023636210","display_name":"Jaehun Han","orcid":null},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehun Han","raw_affiliation_strings":["NAVER LABS, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"NAVER LABS, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011945815","display_name":"Joonho Seo","orcid":"https://orcid.org/0000-0003-0330-1805"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonho Seo","raw_affiliation_strings":["NAVER LABS, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"NAVER LABS, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I60922564"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343642","display_name":"Minsu Kim","orcid":"https://orcid.org/0000-0003-4472-0926"},"institutions":[{"id":"https://openalex.org/I60922564","display_name":"Naver (South Korea)","ror":"https://ror.org/04nzrnx83","country_code":"KR","type":"company","lineage":["https://openalex.org/I60922564"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minsu Kim","raw_affiliation_strings":["NAVER LABS, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"NAVER LABS, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I60922564"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5102865709"],"corresponding_institution_ids":["https://openalex.org/I60922564"],"apc_list":null,"apc_paid":null,"fwci":1.8558,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.88559361,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3363","last_page":"3370"},"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9994000196456909,"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"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8766060471534729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7358101606369019},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7100893259048462},{"id":"https://openalex.org/keywords/retraining","display_name":"Retraining","score":0.6937694549560547},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.6421000361442566},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5633673667907715},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5370575189590454},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5005733966827393},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4896584153175354},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.4887213706970215},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48673155903816223},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.42061516642570496},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14290103316307068},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07677942514419556}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8766060471534729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7358101606369019},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7100893259048462},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.6937694549560547},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.6421000361442566},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5633673667907715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5370575189590454},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5005733966827393},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4896584153175354},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.4887213706970215},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48673155903816223},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.42061516642570496},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14290103316307068},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07677942514419556},{"id":"https://openalex.org/C155202549","wikidata":"https://www.wikidata.org/wiki/Q178803","display_name":"International trade","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra40945.2020.9197159","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra40945.2020.9197159","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W192919555","https://openalex.org/W567721252","https://openalex.org/W1518788040","https://openalex.org/W1527117961","https://openalex.org/W1548797027","https://openalex.org/W1586102543","https://openalex.org/W2064675550","https://openalex.org/W2117211893","https://openalex.org/W2132057084","https://openalex.org/W2142971854","https://openalex.org/W2168405694","https://openalex.org/W2169528473","https://openalex.org/W2440926996","https://openalex.org/W2604216058","https://openalex.org/W2736601468","https://openalex.org/W2763110165","https://openalex.org/W2766614170","https://openalex.org/W2781726626","https://openalex.org/W2783375473","https://openalex.org/W2785324569","https://openalex.org/W2787938642","https://openalex.org/W2889987506","https://openalex.org/W2904246096","https://openalex.org/W2912063360","https://openalex.org/W2951266961","https://openalex.org/W2962717849","https://openalex.org/W2962887844","https://openalex.org/W2962917939","https://openalex.org/W2962943921","https://openalex.org/W2962954724","https://openalex.org/W2963821308","https://openalex.org/W2963923407","https://openalex.org/W2964177756","https://openalex.org/W2964198579","https://openalex.org/W2964199361","https://openalex.org/W2964263543","https://openalex.org/W2967847744","https://openalex.org/W3006334608","https://openalex.org/W4289288058","https://openalex.org/W4321392130","https://openalex.org/W6616173779","https://openalex.org/W6631031103","https://openalex.org/W6632959618","https://openalex.org/W6718190810","https://openalex.org/W6739585900","https://openalex.org/W6741002519","https://openalex.org/W6744156861","https://openalex.org/W6745744936","https://openalex.org/W6747473740","https://openalex.org/W6747912417","https://openalex.org/W6748210908","https://openalex.org/W6748839928","https://openalex.org/W6753526802","https://openalex.org/W6753960536","https://openalex.org/W6757592117","https://openalex.org/W6764214684"],"related_works":["https://openalex.org/W2937325523","https://openalex.org/W4205377104","https://openalex.org/W4388963713","https://openalex.org/W257970033","https://openalex.org/W4221159071","https://openalex.org/W4391212565","https://openalex.org/W2911102221","https://openalex.org/W4285602503","https://openalex.org/W4281387587","https://openalex.org/W2943672508"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1],"learning":[2,101],"(RL)":[3],"is":[4],"being":[5],"actively":[6],"studied":[7],"for":[8],"robot":[9],"navigation":[10,25,76,125],"due":[11],"to":[12,55,83,103,132,138],"its":[13,81,130],"promise":[14],"of":[15,38,45,63,87,113],"superior":[16],"performance":[17,135],"and":[18,36,89,127],"robustness.":[19],"However,":[20],"most":[21],"existing":[22,58],"deep":[23,74,100],"RL":[24,75],"agents":[26],"are":[27],"trained":[28],"using":[29],"fixed":[30],"parameters,":[31],"such":[32,57],"as":[33],"maximum":[34],"velocities":[35],"weightings":[37],"reward":[39,90],"components.":[40],"Since":[41],"the":[42,49],"optimal":[43],"choice":[44],"parameters":[46,88,106],"depends":[47],"on":[48],"use-case,":[50],"it":[51],"can":[52,79,122],"be":[53],"difficult":[54],"deploy":[56],"methods":[59],"in":[60,146],"a":[61,72,84,98,110,133],"variety":[62],"real-world":[64,147],"service":[65],"scenarios.":[66,148],"In":[67],"this":[68],"paper,":[69],"we":[70,96],"propose":[71],"novel":[73],"method":[77,102,121,145],"that":[78,107,119],"adapt":[80,129],"policy":[82,131],"wide":[85],"range":[86],"functions":[91],"without":[92],"expensive":[93],"retraining.":[94],"Additionally,":[95],"explore":[97],"Bayesian":[99],"optimize":[104],"these":[105],"requires":[108],"only":[109],"small":[111],"amount":[112],"preference":[114],"data.":[115],"We":[116,141],"empirically":[117],"show":[118],"our":[120,144],"learn":[123],"diverse":[124],"skills":[126],"quickly":[128],"given":[134],"metric":[136],"or":[137],"human":[139],"preference.":[140],"also":[142],"demonstrate":[143]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}