{"id":"https://openalex.org/W4220702043","doi":"https://doi.org/10.1145/3526107","title":"<i>Here\u2019s What I\u2019ve Learned:</i> Asking Questions that Reveal Reward Learning","display_name":"<i>Here\u2019s What I\u2019ve Learned:</i> Asking Questions that Reveal Reward Learning","publication_year":2022,"publication_date":"2022-03-26","ids":{"openalex":"https://openalex.org/W4220702043","doi":"https://doi.org/10.1145/3526107"},"language":"en","primary_location":{"id":"doi:10.1145/3526107","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3526107","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3526107","source":{"id":"https://openalex.org/S4210193251","display_name":"ACM Transactions on Human-Robot Interaction","issn_l":"2573-9522","issn":["2573-9522"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Human-Robot Interaction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3526107","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071429330","display_name":"Soheil Habibian","orcid":"https://orcid.org/0000-0003-4103-4664"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Soheil Habibian","raw_affiliation_strings":["Virginia Tech, Blacksburg, VA"],"raw_orcid":"https://orcid.org/0000-0003-4103-4664","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, VA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084085793","display_name":"Ananth Jonnavittula","orcid":"https://orcid.org/0000-0002-0711-2051"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ananth Jonnavittula","raw_affiliation_strings":["Virginia Tech, Blacksburg, VA"],"raw_orcid":"https://orcid.org/0000-0002-0711-2051","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, VA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063608480","display_name":"Dylan P. Losey","orcid":"https://orcid.org/0000-0002-8787-5293"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dylan P. Losey","raw_affiliation_strings":["Virginia Tech, Blacksburg, VA"],"raw_orcid":"https://orcid.org/0000-0002-8787-5293","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, VA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071429330"],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":null,"apc_paid":null,"fwci":1.6648,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86022873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"11","issue":"4","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9959999918937683,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9932000041007996,"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/robot","display_name":"Robot","score":0.810233473777771},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6611924171447754},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.643631637096405},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5743919610977173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5621079802513123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5517697334289551},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5497570037841797},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5467005968093872},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5159750580787659},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4528527855873108},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.440408855676651},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.24706214666366577},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14432355761528015}],"concepts":[{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.810233473777771},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6611924171447754},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.643631637096405},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5743919610977173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5621079802513123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5517697334289551},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5497570037841797},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5467005968093872},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5159750580787659},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4528527855873108},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.440408855676651},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.24706214666366577},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14432355761528015},{"id":"https://openalex.org/C136264566","wikidata":"https://www.wikidata.org/wiki/Q159810","display_name":"Economy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3526107","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3526107","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3526107","source":{"id":"https://openalex.org/S4210193251","display_name":"ACM Transactions on Human-Robot Interaction","issn_l":"2573-9522","issn":["2573-9522"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Human-Robot Interaction","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3526107","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3526107","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3526107","source":{"id":"https://openalex.org/S4210193251","display_name":"ACM Transactions on Human-Robot Interaction","issn_l":"2573-9522","issn":["2573-9522"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Human-Robot Interaction","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220702043.pdf","grobid_xml":"https://content.openalex.org/works/W4220702043.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W33891176","https://openalex.org/W187005120","https://openalex.org/W218896052","https://openalex.org/W1494545093","https://openalex.org/W1680189815","https://openalex.org/W1837766154","https://openalex.org/W1965913147","https://openalex.org/W1966354121","https://openalex.org/W1999874108","https://openalex.org/W2031485595","https://openalex.org/W2151516755","https://openalex.org/W2210387432","https://openalex.org/W2251589446","https://openalex.org/W2293700449","https://openalex.org/W2528234499","https://openalex.org/W2588978360","https://openalex.org/W2594227402","https://openalex.org/W2602753196","https://openalex.org/W2735318784","https://openalex.org/W2883171104","https://openalex.org/W2889659926","https://openalex.org/W2913210897","https://openalex.org/W2938095857","https://openalex.org/W2939047085","https://openalex.org/W2962937519","https://openalex.org/W2963240056","https://openalex.org/W2966379335","https://openalex.org/W2981731882","https://openalex.org/W3015812362","https://openalex.org/W3017545672","https://openalex.org/W3091627088","https://openalex.org/W3101773824","https://openalex.org/W3101780148","https://openalex.org/W3142707146","https://openalex.org/W3197594072","https://openalex.org/W4205632023","https://openalex.org/W4289288058","https://openalex.org/W4297787004","https://openalex.org/W6774590752"],"related_works":["https://openalex.org/W2937325523","https://openalex.org/W4205377104","https://openalex.org/W257970033","https://openalex.org/W1994181006","https://openalex.org/W2911102221","https://openalex.org/W4281387587","https://openalex.org/W2943672508","https://openalex.org/W4320918405","https://openalex.org/W4383737174","https://openalex.org/W4285602503"],"abstract_inverted_index":{"Robots":[0],"can":[1,222],"learn":[2,302],"from":[3,56,131,175,263],"humans":[4],"by":[5],"asking":[6],"questions.":[7],"In":[8,167],"these":[9,107,233],"questions,":[10],"the":[11,20,43,57,79,98,126,132,141,156,165,176,182,190,211,226,231,264,269,297,317],"robot":[12,74,89,99,110,157,191,251,254],"demonstrates":[13],"a":[14,145,218,239,253],"few":[15],"different":[16],"behaviors":[17],"and":[18,66,193,216,243,250,287,325],"asks":[19],"human":[21,60,212,249,265,270,318],"for":[22,37,113,257],"their":[23,206],"favorite.":[24],"But":[25,50],"how":[26],"should":[27,93],"robots":[28,35,200,221],"choose":[29],"which":[30,295],"questions":[31,39,53,87,115,187,203,227,234,245],"to":[32,76,85,105,163,201,204,210,224,230,272,316],"ask?":[33],"Today\u2019s":[34],"optimize":[36],"informative":[38,52,114,242],"that":[40,124,155,220,246,255,293],"actively":[41,260],"probe":[42],"human\u2019s":[44,177,183,298],"preferences":[45],"as":[46,48,304,306],"efficiently":[47],"possible.":[49],"while":[51,266,309],"make":[54,205],"sense":[55],"robot\u2019s":[58,186],"perspective,":[59],"onlookers":[61],"may":[62],"find":[63,292],"them":[64],"arbitrary":[65],"misleading":[67],".":[68],"For":[69],"example,":[70],"consider":[71,296],"an":[72],"assistive":[73],"learning":[75,174,207],"put":[77],"away":[78],"dishes.":[80,108],"Based":[81],"on":[82,118],"your":[83],"answers":[84],"previous":[86],"this":[88,119,150,168,258],"knows":[90],"where":[91,162],"it":[92,121,276],"stack":[94,140,164],"each":[95],"dish;":[96],"however,":[97],"is":[100,158],"unsure":[101],"about":[102,161],"right":[103],"height":[104],"carry":[106,125],"A":[109],"optimizing":[111],"only":[112],"focuses":[116],"purely":[117],"height:":[120],"shows":[122],"trajectories":[123],"plates":[127],"near":[128],"or":[129,137],"far":[130],"table,":[133],"regardless":[134],"of":[135,300,321],"whether":[136],"not":[138,195],"they":[139,228,313],"dishes":[142],"correctly.":[143],"As":[144],"result,":[146],"when":[147],"we":[148,152,170],"see":[149],"question,":[151],"mistakenly":[153],"think":[154],"still":[159],"confused":[160],"dishes!":[166],"article,":[169],"formalize":[171],"active":[172],"preference-based":[173],"perspective.":[178],"We":[179,214,236,279,291],"hypothesize":[180],"that\u2014from":[181],"point-of-view":[184],"\u2014the":[185],"reveal":[188],"what":[189,275,312],"has":[192,194,277],"learned.":[196,278],"Our":[197],"insight":[198],"enables":[199],"use":[202],"process":[208],"transparent":[209],"operator.":[213,319],"develop":[215],"test":[217],"model":[219],"leverage":[223],"relate":[225],"ask":[229],"information":[232,262],"reveal.":[235],"then":[237],"introduce":[238],"tradeoff":[240,259],"between":[241],"revealing":[244],"considers":[247],"both":[248],"perspectives:":[252],"optimizes":[256],"gathers":[261],"simultaneously":[267],"keeping":[268],"up":[271],"date":[273],"with":[274],"evaluate":[280],"our":[281,322],"approach":[282],"across":[283],"simulations,":[284],"online":[285],"surveys,":[286],"in-person":[288],"user":[289,323],"studies.":[290],"robots,":[294],"point":[299],"view":[301],"just":[303],"quickly":[305],"state-of-the-art":[307],"baselines":[308],"also":[310],"communicating":[311],"have":[314],"learned":[315],"Videos":[320],"studies":[324],"results":[326],"are":[327],"available":[328],"here:":[329],"https://youtu.be/tC6y_jHN7Vw.":[330]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}