{"id":"https://openalex.org/W4389666480","doi":"https://doi.org/10.1109/iros55552.2023.10342458","title":"From \u201cThumbs Up\u201d to \u201c10 out of 10\u201d: Reconsidering Scalar Feedback in Interactive Reinforcement Learning","display_name":"From \u201cThumbs Up\u201d to \u201c10 out of 10\u201d: Reconsidering Scalar Feedback in Interactive Reinforcement Learning","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4389666480","doi":"https://doi.org/10.1109/iros55552.2023.10342458"},"language":"en","primary_location":{"id":"doi:10.1109/iros55552.2023.10342458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5062917240","display_name":"Hang Yu","orcid":"https://orcid.org/0000-0003-3444-9992"},"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":"Hang Yu","raw_affiliation_strings":["Tufts University, School of Engineering, Computer Science,Medford,Massachusetts,United States of America","Tufts University, School of Engineering, Computer Science, Medford, Massachusetts, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University, School of Engineering, Computer Science,Medford,Massachusetts,United States of America","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Tufts University, School of Engineering, Computer Science, Medford, Massachusetts, United States of America","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, School of Engineering, Computer Science,Medford,Massachusetts,United States of America","Tufts University, School of Engineering, Computer Science, Medford, Massachusetts, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University, School of Engineering, Computer Science,Medford,Massachusetts,United States of America","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Tufts University, School of Engineering, Computer Science, Medford, Massachusetts, United States of America","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072240993","display_name":"Katherine H. Allen","orcid":"https://orcid.org/0009-0008-2240-1696"},"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":"Katherine H. Allen","raw_affiliation_strings":["Tufts University School of Engineering, Mechanical Engineering,Medford,Massachusetts,United States of America","Tufts University School of Engineering, Mechanical Engineering, Medford, Massachusetts, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University School of Engineering, Mechanical Engineering,Medford,Massachusetts,United States of America","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Tufts University School of Engineering, Mechanical Engineering, Medford, Massachusetts, United States of America","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, School of Engineering, Computer Science,Medford,Massachusetts,United States of America","Tufts University, School of Engineering, Computer Science, Medford, Massachusetts, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University, School of Engineering, Computer Science,Medford,Massachusetts,United States of America","institution_ids":["https://openalex.org/I121934306"]},{"raw_affiliation_string":"Tufts University, School of Engineering, Computer Science, Medford, Massachusetts, United States of America","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":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4121","last_page":"4128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11675","display_name":"Open Source Software Innovations","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11675","display_name":"Open Source Software Innovations","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9819999933242798,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9732000231742859,"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/scalar","display_name":"Scalar (mathematics)","score":0.6942281723022461},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.6908329129219055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.572787880897522},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.557332456111908},{"id":"https://openalex.org/keywords/negative-feedback","display_name":"Negative feedback","score":0.4517171382904053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40385016798973083},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.38554590940475464},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36970454454421997},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2557642459869385},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.19228875637054443},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.07287821173667908}],"concepts":[{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.6942281723022461},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.6908329129219055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.572787880897522},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.557332456111908},{"id":"https://openalex.org/C93586867","wikidata":"https://www.wikidata.org/wiki/Q62527","display_name":"Negative feedback","level":3,"score":0.4517171382904053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40385016798973083},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.38554590940475464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36970454454421997},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2557642459869385},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.19228875637054443},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.07287821173667908},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros55552.2023.10342458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros55552.2023.10342458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8664611604","display_name":null,"funder_award_id":"IIS 2132887","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Learning":[0,121],"from":[1,66,134],"human":[2,22,25,188],"feedback":[3,26,53,64,89,110,143,152,157,160,169,176,196,199,204],"is":[4,33,144,205],"an":[5],"effective":[6],"way":[7],"to":[8,16,35,91,131],"improve":[9,132],"robotic":[10],"learning":[11,55,133],"in":[12,115,181,211],"exploration-heavy":[13],"tasks.":[14],"Compared":[15],"the":[17,85,98,139],"wide":[18],"application":[19],"of":[20,69],"binary":[21,47,61,95,109,175,195],"feedback,":[23,48,180],"scalar":[24,45,52,63,88,107,135,142,156,168,179,198,203],"has":[27],"been":[28],"used":[29],"less":[30,92],"because":[31],"it":[32],"believed":[34],"be":[36],"noisy":[37],"and":[38,46,49,108,150,154,177,197,202],"unstable.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"compare":[44],"demonstrate":[50],"that":[51,77,141,164,193],"benefits":[54],"when":[56,78],"properly":[57],"handled.":[58],"We":[59,75,123,162],"collected":[60],"or":[62],"respectively":[65],"two":[67],"groups":[68],"crowdworkers":[70],"on":[71,138,159],"a":[72,82,182,206],"robot":[73,183],"task.":[74],"found":[76],"considering":[79],"how":[80],"consistently":[81],"participant":[83],"labeled":[84],"same":[86],"data,":[87],"led":[90],"consistency":[93],"than":[94],"feedback;":[96],"however,":[97],"difference":[99],"vanishes":[100],"if":[101],"small":[102],"mismatches":[103],"are":[104,200],"allowed.":[105],"Additionally,":[106],"show":[111,163,192],"no":[112],"significant":[113],"differences":[114],"their":[116],"correlations":[117],"with":[118,167,186],"key":[119],"Reinforcement":[120,213],"targets.":[122],"then":[124],"introduce":[125],"Stabilizing":[126],"TEacher":[127],"Assessment":[128],"DYnamics":[129],"(STEADY)":[130],"feedback.":[136,189],"Based":[137],"idea":[140],"muti-distributional,":[145],"STEADY":[146,171],"reconstructs":[147],"underlying":[148],"positive":[149],"negative":[151],"distributions":[153],"re-scales":[155],"based":[158],"statistics.":[161],"models":[165],"trained":[166],"+":[170],"outperform":[172],"baselines,":[173],"including":[174],"raw":[178],"reaching":[184],"task":[185],"non-expert":[187],"Our":[190],"results":[191],"both":[194],"dynamic,":[201],"promising":[207],"signal":[208],"for":[209],"use":[210],"interactive":[212],"Learning.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}