{"id":"https://openalex.org/W3208134787","doi":"https://doi.org/10.1109/thms.2021.3116119","title":"Toward Robots\u2019 Behavioral Transparency of Temporal Difference Reinforcement Learning With a Human Teacher","display_name":"Toward Robots\u2019 Behavioral Transparency of Temporal Difference Reinforcement Learning With a Human Teacher","publication_year":2021,"publication_date":"2021-10-20","ids":{"openalex":"https://openalex.org/W3208134787","doi":"https://doi.org/10.1109/thms.2021.3116119","mag":"3208134787"},"language":"en","primary_location":{"id":"doi:10.1109/thms.2021.3116119","is_oa":true,"landing_page_url":"https://doi.org/10.1109/thms.2021.3116119","pdf_url":"https://ieeexplore.ieee.org/ielx7/6221037/9614265/09580746.pdf","source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Human-Machine Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6221037/9614265/09580746.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089787835","display_name":"Marco Matarese","orcid":"https://orcid.org/0000-0003-1719-3745"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Marco Matarese","raw_affiliation_strings":["University of Genova and Italian Institute of Technology, Genova, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1719-3745","affiliations":[{"raw_affiliation_string":"University of Genova and Italian Institute of Technology, Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019426146","display_name":"Alessandra Sciutti","orcid":"https://orcid.org/0000-0002-1056-3398"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandra Sciutti","raw_affiliation_strings":["Italian Institute of Technology, Genova, Italy"],"raw_orcid":"https://orcid.org/0000-0002-1056-3398","affiliations":[{"raw_affiliation_string":"Italian Institute of Technology, Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046028450","display_name":"Francesco Rea","orcid":"https://orcid.org/0000-0001-8535-223X"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Rea","raw_affiliation_strings":["Italian Institute of Technology, Genova, Italy"],"raw_orcid":"https://orcid.org/0000-0001-8535-223X","affiliations":[{"raw_affiliation_string":"Italian Institute of Technology, Genova, Italy","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046630253","display_name":"Silvia Rossi","orcid":"https://orcid.org/0000-0002-3379-1756"},"institutions":[{"id":"https://openalex.org/I71267560","display_name":"University of Naples Federico II","ror":"https://ror.org/05290cv24","country_code":"IT","type":"education","lineage":["https://openalex.org/I71267560"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Silvia Rossi","raw_affiliation_strings":["University of Napoli Federico II, Napoli, Italy"],"raw_orcid":"https://orcid.org/0000-0002-3379-1756","affiliations":[{"raw_affiliation_string":"University of Napoli Federico II, Napoli, Italy","institution_ids":["https://openalex.org/I71267560"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089787835"],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":5.0072,"has_fulltext":true,"cited_by_count":34,"citation_normalized_percentile":{"value":0.95367055,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"51","issue":"6","first_page":"578","last_page":"589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11094","display_name":"Face Recognition and Perception","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9915000200271606,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/icub","display_name":"iCub","score":0.722223699092865},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7188805341720581},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6308079957962036},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6242091655731201},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.5926992893218994},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5925487279891968},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.5708741545677185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49333158135414124},{"id":"https://openalex.org/keywords/behavior-based-robotics","display_name":"Behavior-based robotics","score":0.4839196801185608},{"id":"https://openalex.org/keywords/legibility","display_name":"Legibility","score":0.44935110211372375},{"id":"https://openalex.org/keywords/social-robot","display_name":"Social robot","score":0.42901909351348877},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.42391350865364075},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.4181568920612335},{"id":"https://openalex.org/keywords/robot-control","display_name":"Robot control","score":0.4004809856414795},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.3098618984222412}],"concepts":[{"id":"https://openalex.org/C111151474","wikidata":"https://www.wikidata.org/wiki/Q1653368","display_name":"iCub","level":4,"score":0.722223699092865},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7188805341720581},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6308079957962036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6242091655731201},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.5926992893218994},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5925487279891968},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.5708741545677185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49333158135414124},{"id":"https://openalex.org/C19766214","wikidata":"https://www.wikidata.org/wiki/Q4880688","display_name":"Behavior-based robotics","level":4,"score":0.4839196801185608},{"id":"https://openalex.org/C2779332521","wikidata":"https://www.wikidata.org/wiki/Q1820694","display_name":"Legibility","level":2,"score":0.44935110211372375},{"id":"https://openalex.org/C162947575","wikidata":"https://www.wikidata.org/wiki/Q2005645","display_name":"Social robot","level":5,"score":0.42901909351348877},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.42391350865364075},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.4181568920612335},{"id":"https://openalex.org/C65401140","wikidata":"https://www.wikidata.org/wiki/Q7353385","display_name":"Robot control","level":4,"score":0.4004809856414795},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.3098618984222412},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/thms.2021.3116119","is_oa":true,"landing_page_url":"https://doi.org/10.1109/thms.2021.3116119","pdf_url":"https://ieeexplore.ieee.org/ielx7/6221037/9614265/09580746.pdf","source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Human-Machine Systems","raw_type":"journal-article"},{"id":"pmh:oai:zenodo.org:5626070","is_oa":true,"landing_page_url":"https://zenodo.org/record/5626070","pdf_url":"https://zenodo.org/record/5626070","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Human-Machine Systems","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:iris.unige.it:11567/1075430","is_oa":false,"landing_page_url":"http://hdl.handle.net/11567/1075430","pdf_url":null,"source":{"id":"https://openalex.org/S4377196291","display_name":"CINECA IRIS Institutial Research Information System (University of Genoa)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83816512","host_organization_name":"University of Genoa","host_organization_lineage":["https://openalex.org/I83816512"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1109/thms.2021.3116119","is_oa":true,"landing_page_url":"https://doi.org/10.1109/thms.2021.3116119","pdf_url":"https://ieeexplore.ieee.org/ielx7/6221037/9614265/09580746.pdf","source":{"id":"https://openalex.org/S2476799526","display_name":"IEEE Transactions on Human-Machine Systems","issn_l":"2168-2291","issn":["2168-2291","2168-2305"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Human-Machine Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.550000011920929,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1904754548","display_name":null,"funder_award_id":"804388","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3208134787.pdf","grobid_xml":"https://content.openalex.org/works/W3208134787.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W8222043","https://openalex.org/W114159433","https://openalex.org/W121023703","https://openalex.org/W263876593","https://openalex.org/W1509191362","https://openalex.org/W1515851193","https://openalex.org/W1563932406","https://openalex.org/W1849553904","https://openalex.org/W1880373995","https://openalex.org/W1926515346","https://openalex.org/W1977137834","https://openalex.org/W1977655452","https://openalex.org/W1983423649","https://openalex.org/W1992154343","https://openalex.org/W1999633780","https://openalex.org/W2014833927","https://openalex.org/W2024649868","https://openalex.org/W2032568497","https://openalex.org/W2039954205","https://openalex.org/W2045880562","https://openalex.org/W2076957974","https://openalex.org/W2085580502","https://openalex.org/W2104674963","https://openalex.org/W2107726111","https://openalex.org/W2109474021","https://openalex.org/W2111201742","https://openalex.org/W2116157560","https://openalex.org/W2121226869","https://openalex.org/W2151074445","https://openalex.org/W2151226872","https://openalex.org/W2169303093","https://openalex.org/W2260848322","https://openalex.org/W2341171179","https://openalex.org/W2394794665","https://openalex.org/W2474744587","https://openalex.org/W2493628527","https://openalex.org/W2494735004","https://openalex.org/W2579063557","https://openalex.org/W2594336441","https://openalex.org/W2594775242","https://openalex.org/W2614309179","https://openalex.org/W2617211984","https://openalex.org/W2785802062","https://openalex.org/W2791361798","https://openalex.org/W2792021648","https://openalex.org/W2910369714","https://openalex.org/W2950510190","https://openalex.org/W2964333534","https://openalex.org/W2995466467","https://openalex.org/W3000083706","https://openalex.org/W3041202696","https://openalex.org/W3098163860","https://openalex.org/W3147024458","https://openalex.org/W4206288734","https://openalex.org/W4237591687","https://openalex.org/W4248056173","https://openalex.org/W4388250061","https://openalex.org/W6604963999","https://openalex.org/W6608787115","https://openalex.org/W6633638985","https://openalex.org/W6650105374","https://openalex.org/W6677262939","https://openalex.org/W6732627134"],"related_works":["https://openalex.org/W4313562880","https://openalex.org/W2097579122","https://openalex.org/W4288725942","https://openalex.org/W2114801867","https://openalex.org/W2462644085","https://openalex.org/W2724299411","https://openalex.org/W3208134787","https://openalex.org/W1991204540","https://openalex.org/W4205830498","https://openalex.org/W2808171219"],"abstract_inverted_index":{"The":[0,112,134],"high":[1],"request":[2],"for":[3,72],"autonomous":[4],"human\u2013robot":[5],"interaction":[6],"(HRI),":[7],"combined":[8],"with":[9,129,161],"the":[10,27,37,40,65,75,81,93,96,106,109,118,123,130,139,145,180,184,197,214,220,223,244],"potential":[11],"of":[12,29,95,108,183,216,222],"machine":[13],"learning":[14,41,69,153],"(ML)":[15],"techniques,":[16],"allow":[17],"us":[18],"to":[19,36,50,63,150,159,167,174,210,235],"deploy":[20],"ML":[21,30],"mechanisms":[22],"in":[23,45,125,178,195,233],"robot":[24,82,110,140,164,185,206,224,245],"control.":[25],"However,":[26],"use":[28],"can":[31,240],"make":[32,51],"robots\u2019":[33],"behavior":[34],"unclear":[35],"observer":[38],"during":[39,67],"phase.":[42],"Recently,":[43],"transparency":[44,66,78,218],"HRI":[46,73],"has":[47],"been":[48],"investigated":[49],"such":[52],"interactions":[53],"more":[54,176],"comprehensible.":[55],"In":[56,189,201],"this":[57],"work,":[58],"we":[59],"propose":[60],"a":[61,126,168,229,247],"model":[62,76,88,113],"improve":[64],"reinforcement":[68],"(RL)":[70],"tasks":[71],"scenarios:":[74],"supports":[77],"by":[79,117,243],"having":[80],"show":[83],"nonverbal":[84],"emotional-behavioral":[85,102,143],"cues.":[86],"Our":[87],"considered":[89],"human":[90,146],"feedback":[91,238],"as":[92,165,246],"reward":[94],"RL":[97],"algorithm":[98],"and":[99,219],"it":[100],"presents":[101],"responses":[103],"based":[104],"on":[105],"progress":[107],"learning.":[111],"is":[114,148],"managed":[115],"only":[116],"temporal-difference":[119],"error.":[120],"We":[121,226],"tested":[122],"architecture":[124],"teaching":[127],"scenario":[128],"iCub":[131],"humanoid":[132],"robot.":[133],"results":[135],"highlight":[136],"that":[137,239],"when":[138],"expresses":[141],"its":[142,152],"response,":[144],"teacher":[147],"able":[149],"understand":[151],"process":[154],"better.":[155],"Furthermore,":[156],"people":[157],"prefer":[158],"interact":[160],"an":[162],"expressive":[163],"compared":[166],"mechanical":[169],"one.":[170],"Movement-based":[171],"signals":[172],"proved":[173],"be":[175,241],"effective":[177,194],"revealing":[179],"internal":[181],"state":[182],"than":[186],"facial":[187],"expressions.":[188],"particular,":[190],"gaze":[191],"movements":[192,207],"were":[193],"showing":[196],"robot's":[198],"next":[199],"intentions.":[200],"contrast,":[202],"communicating":[203],"uncertainty":[204],"through":[205],"sometimes":[208],"led":[209],"action":[211],"misinterpretation,":[212],"highlighting":[213],"importance":[215],"balancing":[217],"legibility":[221],"goal.":[225],"also":[227],"found":[228],"reliable":[230],"temporal":[231],"window":[232],"which":[234],"register":[236],"teachers\u2019":[237],"used":[242],"reward.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-05-17T08:19:37.847499","created_date":"2021-11-08T00:00:00"}