{"id":"https://openalex.org/W6959457655","doi":"https://doi.org/10.13016/xacc-fxv3","title":"EXPERT-IN-THE-LOOP FOR SEQUENTIAL DECISIONS AND PREDICTIONS","display_name":"EXPERT-IN-THE-LOOP FOR SEQUENTIAL DECISIONS AND PREDICTIONS","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W6959457655","doi":"https://doi.org/10.13016/xacc-fxv3"},"language":"en","primary_location":{"id":"doi:10.13016/xacc-fxv3","is_oa":true,"landing_page_url":"https://doi.org/10.13016/xacc-fxv3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Collection"},"type":"dissertation","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.13016/xacc-fxv3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Brantley, Kiante","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Brantley, Kiante","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7282999753952026,"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":0.7282999753952026,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.04259999841451645,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.017100000753998756,"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/imitation","display_name":"Imitation","score":0.7968999743461609},{"id":"https://openalex.org/keywords/covariate","display_name":"Covariate","score":0.3864000141620636},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.36419999599456787},{"id":"https://openalex.org/keywords/interactive-learning","display_name":"Interactive Learning","score":0.3617999851703644},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.35569998621940613},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.29179999232292175}],"concepts":[{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.7968999743461609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6912000179290771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6093000173568726},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5590999722480774},{"id":"https://openalex.org/C119043178","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Covariate","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.36419999599456787},{"id":"https://openalex.org/C2776716048","wikidata":"https://www.wikidata.org/wiki/Q6045290","display_name":"Interactive Learning","level":2,"score":0.3617999851703644},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C34868163","wikidata":"https://www.wikidata.org/wiki/Q5141211","display_name":"Cognitive imitation","level":3,"score":0.2847000062465668},{"id":"https://openalex.org/C24138899","wikidata":"https://www.wikidata.org/wiki/Q17141258","display_name":"Instance-based learning","level":3,"score":0.28189998865127563},{"id":"https://openalex.org/C115903097","wikidata":"https://www.wikidata.org/wiki/Q7094097","display_name":"Online machine learning","level":3,"score":0.27970001101493835},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.26249998807907104}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.13016/xacc-fxv3","is_oa":true,"landing_page_url":"https://doi.org/10.13016/xacc-fxv3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Collection"}],"best_oa_location":{"id":"doi:10.13016/xacc-fxv3","is_oa":true,"landing_page_url":"https://doi.org/10.13016/xacc-fxv3","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Collection"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6862454414367676}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Sequential":[0],"decisions":[1,33,154],"and":[2,12,34,99,120,126,155,212,292,305,314,332],"predictions":[3,35],"are":[4],"common":[5],"problems":[6,309],"in":[7,31,39,63,81,96,132,149,181,289],"natural":[8],"language":[9],"processing,":[10],"robotics,":[11],"video":[13],"games.":[14],"Essentially,":[15],"an":[16,20,79,94,147,195,257,270,325,349],"agent":[17],"interacts":[18],"with":[19,187],"environment":[21],"to":[22,25,41,72,122,194,214,269,295],"learn":[23],"how":[24],"solve":[26],"a":[27,90,106,188,205,228,278,329],"particular":[28,330],"problem.":[29],"Research":[30],"sequential":[32,97,153],"has":[36,50,105],"increased":[37],"due":[38],"part":[40],"the":[42,53,64,82,150,160,177,216,248],"success":[43,49],"of":[44,55,135,145,164,218,255,263,320,357],"reinforcement":[45,272],"learning.":[46,137,169,224,239],"However,":[47],"this":[48,124,186,208,290],"come":[51],"at":[52],"cost":[54],"algorithms":[56,75,245,266,288],"being":[57],"very":[58],"data":[59,253],"inefficient,":[60],"making":[61],"learning":[62,88,104,173,192,233,265,273,304,324,346],"real":[65],"world":[66],"difficult.":[67],"Our":[68],"primary":[69],"goal":[70],"is":[71,89,200,210],"make":[73],"these":[74,244,317],"more":[76],"data-efficient":[77],"using":[78,93,146,251,316],"expert":[80,95,148,350],"loop":[83,151],"(e.g.,":[84],"imitation":[85,103,136,165,168,172,191,223,232,242,264,303,345],"learning).":[86],"Imitation":[87,238],"technique":[91],"for":[92,152,221],"decision":[98],"prediction":[100,298],"problems.":[101,300],"Naive":[102],"covariate":[107,178,249],"shift":[108,179,250],"problem":[109,180,331],"(i.e.,":[110],"training":[111],"distribution":[112],"differs":[113],"from":[114,282],"test":[115],"distribution).":[116],"We":[117,225,285,337],"propose":[118,204],"methods":[119],"ideas":[121],"address":[123,127,247],"issue":[125],"other":[128],"issues":[129,175],"that":[130,275,327,341],"arise":[131],"different":[133],"styles":[134],"In":[138],"particular,":[139],"we":[140,158,203],"study":[141,159],"three":[142],"broad":[143],"areas":[144],"predictions.":[156],"First,":[157],"most":[161],"popular":[162],"category":[163,230,262,291],"learning,":[166,243],"interactive":[167,171,197,222,241,259,306],"Although":[170],"addresses":[174],"around":[176],"naive":[182],"imitation,":[183,307],"it":[184],"does":[185],"trade-off.":[189],"Interactive":[190],"assumesaccess":[193],"online":[196,258],"expert,":[198],"which":[199],"unrealistic.":[201],"Instead,":[202],"setting":[206],"where":[207,348],"assumption":[209],"realistic":[211],"attempt":[213],"reduce":[215],"amount":[217],"queries":[219],"needed":[220],"further":[226],"introduce":[227,338],"new":[229],"on":[231],"algorithm":[234,326],"called,":[235],"Reward-":[236],"Learning":[237],"Unlike":[240],"only":[246],"demonstration":[252,283,352],"instead":[254,356],"querying":[256],"expert.":[260],"This":[261],"assumes":[267],"access":[268],"underlying":[271],"algorithm,":[274],"can":[276],"optimize":[277],"reward":[279],"function":[280],"learned":[281],"data.":[284],"benchmark":[286],"all":[287],"relate":[293],"them":[294],"modern":[296],"structured":[297],"NLP":[299],"Beyond":[301],"reward-learning":[302],"some":[308],"cannot":[310],"be":[311],"naturally":[312],"expressed":[313],"solved":[315],"two":[318],"categories":[319],"algorithms.":[321],"For":[322],"example,":[323],"solves":[328],"also":[333],"satisfies":[334],"safety":[335],"constraints.":[336],"expert-in-the-loop":[339],"techniques":[340],"extend":[342],"beyond":[343],"traditional":[344],"paradigms,":[347],"provides":[351],"features":[353],"or":[354],"constraints,":[355],"state-action":[358],"pairs.":[359]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}