{"id":"https://openalex.org/W4392633674","doi":"https://doi.org/10.1145/3610977.3634925","title":"Modeling Variation in Human Feedback with User Inputs: An Exploratory Methodology","display_name":"Modeling Variation in Human Feedback with User Inputs: An Exploratory Methodology","publication_year":2024,"publication_date":"2024-03-10","ids":{"openalex":"https://openalex.org/W4392633674","doi":"https://doi.org/10.1145/3610977.3634925"},"language":"en","primary_location":{"id":"doi:10.1145/3610977.3634925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610977.3634925","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610977.3634925","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3610977.3634925","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069962923","display_name":"Jindan Huang","orcid":"https://orcid.org/0009-0000-1512-2623"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jindan Huang","raw_affiliation_strings":["Tufts University, Medford, MA, USA"],"raw_orcid":"https://orcid.org/0009-0000-1512-2623","affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017028387","display_name":"Reuben M. Aronson","orcid":"https://orcid.org/0000-0002-8615-3715"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reuben M. Aronson","raw_affiliation_strings":["Tufts University, Medford, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8615-3715","affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077011363","display_name":"Elaine Schaertl Short","orcid":"https://orcid.org/0000-0002-4789-9979"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elaine Schaertl Short","raw_affiliation_strings":["Tufts University, Medford, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4789-9979","affiliations":[{"raw_affiliation_string":"Tufts University, Medford, MA, USA","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I121934306"],"apc_list":null,"apc_paid":null,"fwci":2.4892,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90433868,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"303","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9908000230789185,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9282000064849854,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8237278461456299},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.7752153873443604},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.731606662273407},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5753021240234375},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5620042085647583},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5132277011871338},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"Human-in-the-loop","score":0.5036172270774841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4620508551597595},{"id":"https://openalex.org/keywords/feedback-loop","display_name":"Feedback loop","score":0.4493541717529297},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.4467219412326813},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41932910680770874},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37130114436149597}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237278461456299},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.7752153873443604},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.731606662273407},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5753021240234375},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5620042085647583},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5132277011871338},{"id":"https://openalex.org/C2780626000","wikidata":"https://www.wikidata.org/wiki/Q5936775","display_name":"Human-in-the-loop","level":2,"score":0.5036172270774841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4620508551597595},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.4493541717529297},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4467219412326813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41932910680770874},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37130114436149597},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3610977.3634925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610977.3634925","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610977.3634925","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3610977.3634925","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3610977.3634925","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3610977.3634925","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4392633674.pdf"},"referenced_works_count":41,"referenced_works":["https://openalex.org/W197704362","https://openalex.org/W1655830068","https://openalex.org/W2003238113","https://openalex.org/W2074056782","https://openalex.org/W2086845715","https://openalex.org/W2098441518","https://openalex.org/W2098584016","https://openalex.org/W2109504799","https://openalex.org/W2110064869","https://openalex.org/W2118756286","https://openalex.org/W2127135847","https://openalex.org/W2151074445","https://openalex.org/W2156869222","https://openalex.org/W2164419340","https://openalex.org/W2168108292","https://openalex.org/W2302703641","https://openalex.org/W2560674852","https://openalex.org/W2580300496","https://openalex.org/W2796550359","https://openalex.org/W2837981523","https://openalex.org/W2889659926","https://openalex.org/W2909713847","https://openalex.org/W2957624498","https://openalex.org/W2963489214","https://openalex.org/W3009356492","https://openalex.org/W3032916997","https://openalex.org/W3038618902","https://openalex.org/W3039116038","https://openalex.org/W3039772337","https://openalex.org/W3126966255","https://openalex.org/W3135497281","https://openalex.org/W3187304456","https://openalex.org/W4283742149","https://openalex.org/W4310922000","https://openalex.org/W4312539161","https://openalex.org/W4316662143","https://openalex.org/W4323870299","https://openalex.org/W4389666480","https://openalex.org/W6677180584","https://openalex.org/W6696265566","https://openalex.org/W6730844258"],"related_works":["https://openalex.org/W2914522629","https://openalex.org/W4288099294","https://openalex.org/W4306697907","https://openalex.org/W4386728952","https://openalex.org/W3091793048","https://openalex.org/W2782058284","https://openalex.org/W3103937890","https://openalex.org/W3081671202","https://openalex.org/W2238043057","https://openalex.org/W4248476739"],"abstract_inverted_index":{"To":[0,75],"expedite":[1],"the":[2,55,120,142,177,186],"development":[3],"process":[4],"of":[5,79,110,122,145],"interactive":[6],"reinforcement":[7],"learning":[8,143],"(IntRL)":[9],"algorithms,":[10],"prior":[11,115],"work":[12],"often":[13],"uses":[14],"perfect":[15,126],"oracles":[16,26,80,127,189,203],"as":[17],"simulated":[18,202],"human":[19,60,93,191],"teachers":[20],"to":[21,40,52,65,99,128,159,184],"furnish":[22],"feedback":[23,39,49,94,111,123,178],"signals.":[24],"These":[25],"typically":[27],"derive":[28],"from":[29,125,167,207],"ground-truth":[30],"knowledge":[31],"or":[32,67],"optimal":[33],"policies,":[34],"providing":[35],"dense":[36],"and":[37,182,190],"error-free":[38],"a":[41,87,100,105,150,156,197],"robot":[42],"learner":[43],"without":[44],"delay.":[45],"However,":[46],"this":[47,77],"machine-like":[48],"behavior":[50],"fails":[51],"accurately":[53],"represent":[54],"diverse":[56],"patterns":[57],"observed":[58],"in":[59,71,81,92,114,169],"feedback,":[61],"which":[62],"may":[63],"lead":[64],"unstable":[66],"unexpected":[68],"algorithm":[69,148],"performance":[70,144],"real-world":[72],"human-robot":[73],"interaction.":[74],"alleviate":[76],"limitation":[78],"oversimplifying":[82],"user":[83],"behavior,":[84],"we":[85],"propose":[86],"method":[88,195],"for":[89],"modeling":[90,173],"variation":[91,112,179],"that":[95],"can":[96,139,164],"be":[97,165],"applied":[98],"standard":[101],"oracle.":[102],"We":[103,133,153],"present":[104,176],"model":[106,118,137,163],"with":[107],"5":[108],"dimensions":[109],"identified":[113],"work.":[116],"This":[117],"enables":[119],"modification":[121],"outputs":[124],"introduce":[129],"more":[130],"human-like":[131],"features.":[132],"demonstrate":[134],"how":[135,161],"each":[136],"attribute":[138],"impact":[140],"on":[141],"an":[146],"IntRL":[147],"through":[149],"simulation":[151],"experiment.":[152],"also":[154],"conduct":[155],"proof-of-concept":[157],"study":[158],"illustrate":[160],"our":[162,194],"populated":[166],"people":[168],"two":[170],"ways.":[171],"The":[172],"results":[174],"intuitively":[175],"among":[180],"participants":[181],"help":[183],"explain":[185],"mismatch":[187],"between":[188],"teachers.":[192],"Overall,":[193],"is":[196],"promising":[198],"step":[199],"towards":[200],"refining":[201],"by":[204],"incorporating":[205],"insights":[206],"real":[208],"users.":[209]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}