{"id":"https://openalex.org/W7134845572","doi":"https://doi.org/10.1145/3757279.3785589","title":"What You Reward Is What You Learn: Comparing Rewards for Online Speech Policy Optimization in Public HRI","display_name":"What You Reward Is What You Learn: Comparing Rewards for Online Speech Policy Optimization in Public HRI","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134845572","doi":"https://doi.org/10.1145/3757279.3785589"},"language":null,"primary_location":{"id":"doi:10.1145/3757279.3785589","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757279.3785589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","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/A5128663782","display_name":"Sichao Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sichao Song","raw_affiliation_strings":["CyberAgent, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-8408-4437","affiliations":[{"raw_affiliation_string":"CyberAgent, Tokyo, Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032387791","display_name":"Yuki Okafuji","orcid":"https://orcid.org/0000-0002-9547-3681"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Okafuji","raw_affiliation_strings":["CyberAgent, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-9547-3681","affiliations":[{"raw_affiliation_string":"CyberAgent, Tokyo, Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081429958","display_name":"Kaito Ariu","orcid":"https://orcid.org/0000-0001-6286-9906"},"institutions":[{"id":"https://openalex.org/I4210089607","display_name":"CyberAgent (Japan)","ror":"https://ror.org/0060jg679","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210089607"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kaito Ariu","raw_affiliation_strings":["CyberAgent, Tokyo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-6286-9906","affiliations":[{"raw_affiliation_string":"CyberAgent, Tokyo, Japan","institution_ids":["https://openalex.org/I4210089607"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009757349","display_name":"Amy Koike","orcid":"https://orcid.org/0009-0000-9088-6578"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amy Koike","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, USA"],"raw_orcid":"https://orcid.org/0009-0000-9088-6578","affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21180881,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"187","last_page":"195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12415","display_name":"Employer Branding and e-HRM","score":0.045899998396635056,"subfield":{"id":"https://openalex.org/subfields/1407","display_name":"Organizational Behavior and Human Resource Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12415","display_name":"Employer Branding and e-HRM","score":0.045899998396635056,"subfield":{"id":"https://openalex.org/subfields/1407","display_name":"Organizational Behavior and Human Resource Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12593","display_name":"Communication in Education and Healthcare","score":0.039000000804662704,"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/T10970","display_name":"Team Dynamics and Performance","score":0.0272000003606081,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/public-policy","display_name":"Public policy","score":0.36039999127388},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3264999985694885},{"id":"https://openalex.org/keywords/human\u2013robot-interaction","display_name":"Human\u2013robot interaction","score":0.3156999945640564},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.2815999984741211},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.26809999346733093}],"concepts":[{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.47450000047683716},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4726000130176544},{"id":"https://openalex.org/C109986646","wikidata":"https://www.wikidata.org/wiki/Q546113","display_name":"Public policy","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32850000262260437},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.3156999945640564},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.28189998865127563},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27250000834465027},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C522180918","wikidata":"https://www.wikidata.org/wiki/Q18342738","display_name":"Public speaking","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757279.3785589","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3757279.3785589","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM/IEEE International Conference on Human-Robot Interaction","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2039522160","https://openalex.org/W2158319693","https://openalex.org/W2200124539","https://openalex.org/W2269293615","https://openalex.org/W2570651606","https://openalex.org/W2608055108","https://openalex.org/W2736923367","https://openalex.org/W2896395034","https://openalex.org/W2898461817","https://openalex.org/W2900377066","https://openalex.org/W2943916261","https://openalex.org/W2945173102","https://openalex.org/W2948208238","https://openalex.org/W2962849870","https://openalex.org/W2965916140","https://openalex.org/W3114195756","https://openalex.org/W3165360095","https://openalex.org/W4206530644","https://openalex.org/W4243724405","https://openalex.org/W4409720015","https://openalex.org/W4410298262","https://openalex.org/W4413917211","https://openalex.org/W7082260771"],"related_works":[],"abstract_inverted_index":{"Designing":[0],"policies":[1,141],"that":[2,99,116],"are":[3],"both":[4],"efficient":[5],"and":[6,14,66,80,94,105],"acceptable":[7],"for":[8,135],"conversational":[9],"service":[10],"robots":[11],"in":[12,43,142],"open":[13],"diverse":[15],"environments":[16],"is":[17],"non-trivial.":[18],"Unlike":[19],"fixed,":[20],"hand-tuned":[21],"parameters,":[22],"online":[23,58,111,137],"learning":[24],"can":[25],"adapt":[26,37],"to":[27,36,70],"non-stationary":[28],"conditions.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33,56,130],"study":[34],"how":[35],"a":[38,47,62],"social":[39],"robot\u2019s":[40],"speech":[41,77,140],"policy":[42,59],"the":[44,110],"wild.":[45],"During":[46],"12-day":[48],"in-situ":[49],"deployment":[50],"with":[51,113],"over":[52],"1,400":[53],"public":[54,144],"encounters,":[55],"cast":[57],"optimization":[60,138],"as":[61],"multi-armed":[63],"bandit":[64],"problem":[65],"use":[67],"Thompson":[68],"sampling":[69],"select":[71],"among":[72],"six":[73],"actions":[74],"defined":[75],"by":[76],"rate":[78],"(slow/normal/fast)":[79],"verbosity":[81],"(concise/detailed).":[82],"We":[83,108],"compare":[84],"three":[85],"complementary":[86],"binary":[87],"rewards\u2013Ru":[88],"(user":[89],"rating),":[90],"Rc":[91],"(conversation":[92],"closure),":[93],"Rt":[95],"(\u22652":[96],"turns)\u2013and":[97],"show":[98],"each":[100],"induces":[101],"distinct":[102],"arm":[103],"distributions":[104],"interaction":[106],"behaviors.":[107],"complement":[109],"results":[112],"offline":[114],"evaluations":[115],"analyze":[117],"contextual":[118],"factors":[119],"(e.g.,":[120],"crowd":[121],"level,":[122],"group":[123],"size)":[124],"using":[125],"video-annotated":[126],"data.":[127],"Taken":[128],"together,":[129],"distill":[131],"ready-to-use":[132],"design":[133],"lessons":[134],"deploying":[136],"of":[139],"real":[143],"HRI":[145],"settings.":[146]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-11T00:00:00"}
