{"id":"https://openalex.org/W4401414913","doi":"https://doi.org/10.1109/icra57147.2024.10611425","title":"Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning","display_name":"Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414913","doi":"https://doi.org/10.1109/icra57147.2024.10611425"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5088032599","display_name":"Siddharth Singi","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddharth Singi","raw_affiliation_strings":["Columbia University,Dept. of Mechanical Engineering,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Dept. of Mechanical Engineering,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103934489","display_name":"Zhanpeng He","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhanpeng He","raw_affiliation_strings":["Columbia University,Dept. of Computer Science,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Dept. of Computer Science,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030842382","display_name":"Alvin Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alvin Pan","raw_affiliation_strings":["Columbia University,Dept. of Computer Science,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Dept. of Computer Science,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070734531","display_name":"Sandip Pravin Patel","orcid":"https://orcid.org/0000-0002-8387-4840"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandip Patel","raw_affiliation_strings":["Columbia University,Dept. of Mechanical Engineering,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Dept. of Mechanical Engineering,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035681753","display_name":"Gunnar A. Sigurdsson","orcid":"https://orcid.org/0000-0001-8967-7322"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gunnar A. Sigurdsson","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018704921","display_name":"Robinson Piramuthu","orcid":"https://orcid.org/0000-0002-1767-8382"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robinson Piramuthu","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004644695","display_name":"Shuran Song","orcid":"https://orcid.org/0000-0002-8768-7356"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuran Song","raw_affiliation_strings":["Amazon Alexa AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon Alexa AI","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087490971","display_name":"Matei Ciocarlie","orcid":"https://orcid.org/0000-0002-8317-4465"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matei Ciocarlie","raw_affiliation_strings":["Columbia University,Dept. of Mechanical Engineering,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,Dept. of Mechanical Engineering,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.556,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.94300422,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7939","last_page":"7945"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9886999726295471,"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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.9571999907493591,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.866188108921051},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.736533522605896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6641398668289185},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.5749987363815308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5081517696380615},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.43676045536994934},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3442074954509735},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32468104362487793},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0937991738319397}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.866188108921051},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.736533522605896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6641398668289185},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.5749987363815308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5081517696380615},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.43676045536994934},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3442074954509735},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32468104362487793},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0937991738319397},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611425","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra57147.2024.10611425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6800000071525574,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1501005121","https://openalex.org/W2042882799","https://openalex.org/W2125612430","https://openalex.org/W2150818585","https://openalex.org/W2156869222","https://openalex.org/W2586067474","https://openalex.org/W2604847142","https://openalex.org/W2799745602","https://openalex.org/W2807588596","https://openalex.org/W2898227854","https://openalex.org/W2950872548","https://openalex.org/W2962730405","https://openalex.org/W2963438456","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2996868001","https://openalex.org/W3164838844","https://openalex.org/W3171912333","https://openalex.org/W3207713159","https://openalex.org/W4298857966","https://openalex.org/W4307001526","https://openalex.org/W4323066453","https://openalex.org/W4386410083","https://openalex.org/W6684921986","https://openalex.org/W6685757253","https://openalex.org/W6706320068","https://openalex.org/W6751629939","https://openalex.org/W6752244597","https://openalex.org/W6764969207"],"related_works":["https://openalex.org/W24774503","https://openalex.org/W4306904969","https://openalex.org/W4288099294","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W4367173559","https://openalex.org/W2782058284","https://openalex.org/W3103937890"],"abstract_inverted_index":{"In":[0,54],"a":[1,4,15,59,68,115,137],"Human-in-the-Loop":[2],"paradigm,":[3],"robotic":[5],"agent":[6,70],"is":[7,34,90],"able":[8],"to":[9,30,41,64,149],"act":[10],"mostly":[11],"autonomously":[12],"in":[13,80],"solving":[14],"task,":[16],"but":[17,46],"can":[18,39,50,108],"request":[19,31],"help":[20],"from":[21,99],"an":[22],"external":[23,73],"expert":[24,141,151],"when":[25,29,75],"needed.":[26],"However,":[27],"knowing":[28],"such":[32],"assistance":[33,74],"critical:":[35],"too":[36,47],"few":[37],"requests":[38,49],"lead":[40],"the":[42,52,81,85,94,97,100,150],"robot":[43],"making":[44],"mistakes,":[45],"many":[48],"overload":[51],"expert.":[53],"this":[55,65,106],"paper,":[56],"we":[57,128],"present":[58],"Reinforcement":[60],"Learning":[61],"based":[62],"approach":[63],"problem,":[66],"where":[67],"semi-autonomous":[69],"asks":[71],"for":[72],"it":[76],"has":[77],"low":[78],"confidence":[79,88],"eventual":[82],"success":[83],"of":[84,96,136,140],"task.":[86],"The":[87],"level":[89],"computed":[91],"by":[92],"estimating":[93],"variance":[95],"return":[98],"current":[101],"state.":[102],"We":[103],"show":[104,129],"that":[105,130],"estimate":[107],"be":[109],"iteratively":[110],"improved":[111],"during":[112],"training":[113,153],"using":[114],"Bellman-like":[116],"recursion.":[117],"On":[118],"discrete":[119],"navigation":[120],"problems":[121],"with":[122],"both":[123],"fully-and":[124],"partially-observable":[125],"state":[126],"information,":[127],"our":[131],"method":[132],"makes":[133],"effective":[134],"use":[135],"limited":[138],"budget":[139],"calls":[142],"at":[143,152],"run-time,":[144],"despite":[145],"having":[146],"no":[147],"access":[148],"time.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}