{"id":"https://openalex.org/W4388623348","doi":"https://doi.org/10.1109/ro-man57019.2023.10309622","title":"Adapting a Teachable Robot\u2019s Dialog Responses using Reinforcement Learning in Teaching Conversation","display_name":"Adapting a Teachable Robot\u2019s Dialog Responses using Reinforcement Learning in Teaching Conversation","publication_year":2023,"publication_date":"2023-08-28","ids":{"openalex":"https://openalex.org/W4388623348","doi":"https://doi.org/10.1109/ro-man57019.2023.10309622"},"language":"en","primary_location":{"id":"doi:10.1109/ro-man57019.2023.10309622","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ro-man57019.2023.10309622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","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/A5063882637","display_name":"R.P. Love","orcid":"https://orcid.org/0000-0001-9879-204X"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rachel Love","raw_affiliation_strings":["Monash University,Department of Electrical and Computer Systems Engineering,Australia","Department of Electrical and Computer Systems Engineering, Monash University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Department of Electrical and Computer Systems Engineering,Australia","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"Department of Electrical and Computer Systems Engineering, Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058482884","display_name":"Edith Law","orcid":"https://orcid.org/0000-0002-7540-075X"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Edith Law","raw_affiliation_strings":["University of Waterloo,David R. Cheriton School of Computer Science,Canada","David R. Cheriton School of Computer Science, University of Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo,David R. Cheriton School of Computer Science,Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"David R. Cheriton School of Computer Science, University of Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075508013","display_name":"Philip R. Cohen","orcid":"https://orcid.org/0000-0003-1303-064X"},"institutions":[{"id":"https://openalex.org/I175669267","display_name":"Carestream (United States)","ror":"https://ror.org/048m16q57","country_code":"US","type":"company","lineage":["https://openalex.org/I175669267"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU","US"],"is_corresponding":false,"raw_author_name":"Philip R. Cohen","raw_affiliation_strings":["Openstream, Inc.,USA","Openstream, Inc., USA","Department of Data Science and Artificial Intelligence, Monash University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Openstream, Inc.,USA","institution_ids":["https://openalex.org/I175669267"]},{"raw_affiliation_string":"Openstream, Inc., USA","institution_ids":["https://openalex.org/I175669267"]},{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072377971","display_name":"Dana Kuli\u0107","orcid":"https://orcid.org/0000-0002-4169-2141"},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dana Kuli\u0107","raw_affiliation_strings":["Monash University,Department of Electrical and Computer Systems Engineering and Department of Mechanical and Aerospace Engineering,Australia","Department of Electrical and Computer Systems Engineering and Department of Mechanical and Aerospace Engineering, Monash University, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University,Department of Electrical and Computer Systems Engineering and Department of Mechanical and Aerospace Engineering,Australia","institution_ids":["https://openalex.org/I56590836"]},{"raw_affiliation_string":"Department of Electrical and Computer Systems Engineering and Department of Mechanical and Aerospace Engineering, Monash University, Australia","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"21","issue":null,"first_page":"2541","last_page":"2548"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9994999766349792,"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":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9980999827384949,"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/T12128","display_name":"AI in Service Interactions","score":0.9951000213623047,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7750845551490784},{"id":"https://openalex.org/keywords/conversation","display_name":"Conversation","score":0.7389278411865234},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.7261336445808411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.665347695350647},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6491160988807678},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5688939094543457},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5588706135749817},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5339934229850769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5142573714256287},{"id":"https://openalex.org/keywords/gaze","display_name":"Gaze","score":0.4702431261539459},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.4637487530708313},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.43978238105773926},{"id":"https://openalex.org/keywords/social-cue","display_name":"Social cue","score":0.4143819808959961},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.15828678011894226},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1369107961654663},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1098153293132782},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.1007051169872284},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.08748093247413635}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7750845551490784},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.7389278411865234},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7261336445808411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.665347695350647},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6491160988807678},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5688939094543457},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5588706135749817},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5339934229850769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5142573714256287},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.4702431261539459},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.4637487530708313},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.43978238105773926},{"id":"https://openalex.org/C10090317","wikidata":"https://www.wikidata.org/wiki/Q7551030","display_name":"Social cue","level":2,"score":0.4143819808959961},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.15828678011894226},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1369107961654663},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1098153293132782},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.1007051169872284},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.08748093247413635},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ro-man57019.2023.10309622","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ro-man57019.2023.10309622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W103982469","https://openalex.org/W1995911123","https://openalex.org/W2006451753","https://openalex.org/W2018132040","https://openalex.org/W2035061933","https://openalex.org/W2053976921","https://openalex.org/W2096284813","https://openalex.org/W2110437072","https://openalex.org/W2169570446","https://openalex.org/W2210403097","https://openalex.org/W2336960426","https://openalex.org/W2526254901","https://openalex.org/W2560862806","https://openalex.org/W2802849722","https://openalex.org/W2808582260","https://openalex.org/W2887260263","https://openalex.org/W2904737914","https://openalex.org/W2905180035","https://openalex.org/W2913258601","https://openalex.org/W2970641574","https://openalex.org/W2975028745","https://openalex.org/W2998670453","https://openalex.org/W3128013500","https://openalex.org/W3163063423","https://openalex.org/W3194517965","https://openalex.org/W3194699395","https://openalex.org/W3195657465","https://openalex.org/W4229536511","https://openalex.org/W4237976213","https://openalex.org/W6768833901","https://openalex.org/W6771822515","https://openalex.org/W6810287229"],"related_works":["https://openalex.org/W2098987383","https://openalex.org/W2025462240","https://openalex.org/W1830656823","https://openalex.org/W4311114586","https://openalex.org/W3204141869","https://openalex.org/W2782048214","https://openalex.org/W1990992754","https://openalex.org/W2012804445","https://openalex.org/W2139347408","https://openalex.org/W2406305024"],"abstract_inverted_index":{"Teachable":[0],"robots":[1],"can":[2,27],"offer":[3],"benefits":[4],"to":[5,19,31,76,89,99,120,125,139,148],"students":[6],"through":[7],"the":[8,55,81,100,107,111,122,149],"use":[9,56],"of":[10,41,57,128],"social":[11,47,62],"behaviours,":[12],"such":[13],"as":[14],"speech,":[15],"gaze,":[16],"and":[17,22,106,146],"gestures,":[18],"promote":[20],"engagement":[21,79],"learning.":[23],"Adapting":[24],"these":[25],"behaviours":[26,60],"deliver":[28],"personalised":[29],"interactions":[30],"better":[32],"suit":[33],"each":[34],"individual.":[35],"There":[36],"is":[37,51,96],"a":[38,71,126],"growing":[39],"body":[40],"research":[42,53],"utilising":[43],"reinforcement":[44],"learning":[45],"in":[46,54,80,110],"robotics,":[48],"however":[49],"there":[50],"limited":[52],"adaptive":[58,67,136],"dialog":[59],"for":[61,70],"robots.":[63],"We":[64],"propose":[65],"an":[66,91,135],"response-selection":[68],"algorithm":[69,95],"teachable":[72],"robot":[73],"which":[74],"aims":[75],"improve":[77],"user":[78,115],"teaching":[82,104],"task.":[83],"The":[84,94,131],"proposed":[85],"approach":[86,137],"uses":[87],"Q-learning":[88],"learn":[90],"individualised":[92],"policy.":[93],"rewarded":[97],"according":[98],"time":[101],"taken":[102],"per":[103],"input,":[105],"amount":[108],"paraphrasing":[109],"user\u2019s":[112],"response.":[113],"A":[114],"study":[116],"has":[117],"been":[118],"conducted":[119],"evaluate":[121],"algorithm,":[123],"compared":[124],"method":[127],"random":[129],"response-selection.":[130],"results":[132],"indicate":[133],"that":[134],"learns":[138],"select":[140],"more":[141],"rewarding":[142],"actions":[143],"over":[144],"time,":[145],"personalise":[147],"individual":[150],"user.":[151]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}