乐胖代购免代理版

{"id":"https://openalex.org/W3038618902","doi":"https://doi.org/10.15607/rss.2020.xvi.055","title":"Learning from Interventions: Human-robot interaction as both explicit and implicit feedback","display_name":"Learning from Interventions: Human-robot interaction as both explicit and implicit feedback","publication_year":2020,"publication_date":"2020-06-30","ids":{"openalex":"https://openalex.org/W3038618902","doi":"https://doi.org/10.15607/rss.2020.xvi.055","mag":"3038618902"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.15607/rss.2020.xvi.055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.15607/rss.2020.xvi.055","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058232636","display_name":"Jonathan Spencer","orcid":"https://orcid.org/0000-0001-5894-132X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Spencer","raw_affiliation_strings":["Princeton University,"],"affiliations":[{"raw_affiliation_string":"Princeton University,","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057995939","display_name":"Sanjiban Choudhury","orcid":"https://orcid.org/0000-0003-2762-8888"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjiban Choudhury","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023240185","display_name":"Matt Barnes","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matt Barnes","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038162737","display_name":"Matthew Schmittle","orcid":null},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Schmittle","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110782105","display_name":"Mung Chiang","orcid":"https://orcid.org/0000-0002-8920-651X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mung Chiang","raw_affiliation_strings":["Princeton University,"],"affiliations":[{"raw_affiliation_string":"Princeton University,","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041274293","display_name":"Peter J. Ramadge","orcid":"https://orcid.org/0000-0002-3282-216X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Ramadge","raw_affiliation_strings":["Princeton University,"],"affiliations":[{"raw_affiliation_string":"Princeton University,","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077719529","display_name":"Siddhartha S Srinivasa","orcid":"https://orcid.org/0000-0002-5091-106X"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siddhartha Srinivasa","raw_affiliation_strings":["University of Washington"],"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.934,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":28,"citation_normalized_percentile":{"value":0.966082,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":95},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9999,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9999,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997,"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":0.9769,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.6465718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6668928},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.6465718},{"id":"https://openalex.org/C27415008","wikidata":"https://www.wikidata.org/wiki/Q7256382","display_name":"Psychological intervention","level":2,"score":0.636482},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6079919},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5980369},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33441454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31994087},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.15607/rss.2020.xvi.055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.15607/rss.2020.xvi.055","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":46,"referenced_works":["https://openalex.org/W1501005121","https://openalex.org/W1872886848","https://openalex.org/W1931877416","https://openalex.org/W1980969546","https://openalex.org/W1986014385","https://openalex.org/W1999874108","https://openalex.org/W2074056782","https://openalex.org/W2077723394","https://openalex.org/W2119388568","https://openalex.org/W2123694750","https://openalex.org/W2124299914","https://openalex.org/W2133552775","https://openalex.org/W2148825261","https://openalex.org/W2154018708","https://openalex.org/W2158349948","https://openalex.org/W2167224731","https://openalex.org/W2295827790","https://openalex.org/W2409942531","https://openalex.org/W2410842990","https://openalex.org/W2527925052","https://openalex.org/W2565370028","https://openalex.org/W2580300496","https://openalex.org/W2593841437","https://openalex.org/W2604325524","https://openalex.org/W2769520592","https://openalex.org/W2783036728","https://openalex.org/W2792089292","https://openalex.org/W2794908222","https://openalex.org/W2902123951","https://openalex.org/W2917084500","https://openalex.org/W2950735232","https://openalex.org/W2951660448","https://openalex.org/W2952217334","https://openalex.org/W2962736495","https://openalex.org/W2963289505","https://openalex.org/W2964132611","https://openalex.org/W2966994213","https://openalex.org/W2969748094","https://openalex.org/W2972268404","https://openalex.org/W3003342008","https://openalex.org/W3004162282","https://openalex.org/W3022429412","https://openalex.org/W3101780148","https://openalex.org/W33732390","https://openalex.org/W4292022450","https://openalex.org/W4300110528"],"related_works":["https://openalex.org/W4380487215","https://openalex.org/W4366818884","https://openalex.org/W4366547574","https://openalex.org/W3205513966","https://openalex.org/W3200191727","https://openalex.org/W3120459843","https://openalex.org/W3042490037","https://openalex.org/W2978665606","https://openalex.org/W2248308732","https://openalex.org/W189465620"],"abstract_inverted_index":{"Scalable":[0],"robot":[1],"learning":[2,25,74,134],"from":[3,27,76,162],"seamless":[4],"human-robot":[5],"interaction":[6],"is":[7,87],"critical":[8],"if":[9],"robots":[10],"are":[11],"to":[12,23,47,59],"solve":[13],"a":[14,48,118,147,154,166],"multitude":[15],"of":[16,29,82,91,104,110,173],"tasks":[17],"in":[18,43,50,69],"the":[19,32,53,57,63,80,102,105,108,111,121],"real":[20,148],"world.Current":[21],"approaches":[22],"imitation":[24],"suffer":[26],"one":[28,33,171],"two":[30],"drawbacks.On":[31],"hand,":[34],"they":[35,55],"rely":[36],"solely":[37],"on":[38,120,146],"off-policy":[39],"human":[40,58,155],"demonstration,":[41],"which":[42,125],"some":[44],"cases":[45],"leads":[46],"mismatch":[49],"train-test":[51],"distribution.On":[52],"other,":[54],"burden":[56],"label":[60],"every":[61],"state":[62],"learner":[64],"visits,":[65],"rendering":[66],"it":[67,145,158],"impractical":[68],"many":[70],"applications.We":[71],"argue":[72],"that":[73,88],"interactively":[75],"expert":[77,92,174],"interventions":[78],"enjoys":[79],"best":[81],"both":[83],"worlds.Our":[84],"key":[85],"insight":[86],"any":[89],"amount":[90],"feedback,":[93],"whether":[94],"by":[95],"intervention":[96],"or":[97,113],"non-intervention,":[98],"provides":[99],"information":[100],"about":[101],"quality":[103],"current":[106],"state,":[107],"optimality":[109],"action,":[112],"both.We":[114],"formalize":[115],"this":[116],"as":[117],"constraint":[119],"learner's":[122],"value":[123],"function,":[124],"we":[126],"can":[127],"efficiently":[128],"learn":[129],"using":[130],"no":[131],"regret,":[132],"online":[133],"techniques.We":[135],"call":[136],"our":[137],"approach":[138],"Expert":[139],"Intervention":[140],"Learning":[141],"(EIL),":[142],"and":[143,149],"evaluate":[144],"simulated":[150],"driving":[151],"task":[152],"with":[153,164],"expert,":[156],"where":[157],"learns":[159],"collision":[160],"avoidance":[161],"scratch":[163],"just":[165],"few":[167],"hundred":[168],"samples":[169],"(about":[170],"minute)":[172],"control.":[175]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3038618902","counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":1}],"updated_date":"2025-01-21T13:24:31.992189","created_date":"2020-07-10"}