{"id":"https://openalex.org/W3094394171","doi":"https://doi.org/10.1145/3383652.3423877","title":"A framework to co-optimize task and social dialogue policies using Reinforcement Learning","display_name":"A framework to co-optimize task and social dialogue policies using Reinforcement Learning","publication_year":2020,"publication_date":"2020-10-19","ids":{"openalex":"https://openalex.org/W3094394171","doi":"https://doi.org/10.1145/3383652.3423877","mag":"3094394171"},"language":"en","primary_location":{"id":"doi:10.1145/3383652.3423877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383652.3423877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Intelligent Virtual Agents","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/50410.html>","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019638904","display_name":"Florian P\u00e9cune","orcid":"https://orcid.org/0000-0002-3235-2575"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Florian Pecune","raw_affiliation_strings":["University of Glasgow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058433199","display_name":"Stacy Marsella","orcid":"https://orcid.org/0000-0002-5711-7934"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stacy Marsella","raw_affiliation_strings":["University of Glasgow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038198443","display_name":"Alankar Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alankar Jain","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9479,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8144708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":1.0,"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/T12031","display_name":"Speech and dialogue systems","score":1.0,"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/T10028","display_name":"Topic Modeling","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9057813882827759},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8525739908218384},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.8139105439186096},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7246948480606079},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.5847827792167664},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.582832396030426},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5541269183158875},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4213276505470276},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41845136880874634},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.17703738808631897}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9057813882827759},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8525739908218384},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.8139105439186096},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7246948480606079},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.5847827792167664},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.582832396030426},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5541269183158875},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4213276505470276},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41845136880874634},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.17703738808631897},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3383652.3423877","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3383652.3423877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th ACM International Conference on Intelligent Virtual Agents","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:230917","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/50410.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:230917","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/50410.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W130649202","https://openalex.org/W407492923","https://openalex.org/W1577202350","https://openalex.org/W2021151961","https://openalex.org/W2084582948","https://openalex.org/W2109636054","https://openalex.org/W2155959475","https://openalex.org/W2156323794","https://openalex.org/W2168490009","https://openalex.org/W2240797648","https://openalex.org/W2564375270","https://openalex.org/W2754576213","https://openalex.org/W2775496038","https://openalex.org/W2901893112","https://openalex.org/W2963262099","https://openalex.org/W2964309167","https://openalex.org/W3013697129","https://openalex.org/W7077478621"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W1600043506","https://openalex.org/W2174703168","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2920931047","https://openalex.org/W337810568"],"abstract_inverted_index":{"One":[0],"of":[1,19,73,140,149,182,197,219,234],"the":[2,11,17,20,28,70,116,121,127,131,159,183,195],"main":[3],"challenges":[4],"for":[5,68,125],"conversational":[6,29,75,102,164,167,242,264],"agents":[7],"is":[8],"to":[9,34,50,62,87,93,136,186,193,210],"select":[10],"optimal":[12,66],"dialogue":[13,96,259],"policy":[14,67,97,260],"based":[15],"on":[16,99,205,262],"state":[18],"interaction.":[21],"This":[22],"challenge":[23,53],"becomes":[24],"even":[25],"harder":[26],"when":[27,178],"agent":[30,91,109,166,214,256],"not":[31],"only":[32],"has":[33],"achieve":[35],"a":[36,55,82,89,107,111,138,153,198,212],"specific":[37],"task,":[38],"but":[39],"also":[40],"aims":[41],"at":[42,115],"building":[43],"rapport.":[44,170,188],"Although":[45],"some":[46],"work":[47],"already":[48],"tried":[49,185],"tackle":[51],"this":[52,78,191,206],"using":[54,215],"Reinforcement":[56],"Learning":[57],"(RL)":[58],"approach,":[59],"they":[60],"tend":[61],"consider":[63],"one":[64,238],"single":[65,154],"all":[69],"users,":[71],"regardless":[72],"their":[74],"goals.":[76,103],"In":[77],"work,":[79],"we":[80,105,119,146,203],"describe":[81],"framework":[83],"that":[84,174,239,248,254],"allows":[85],"us":[86,135],"build":[88,106,187],"RL-based":[90,213,236],"able":[92],"adapt":[94],"its":[95,100,258],"depending":[98,261],"user's":[101],"After":[104],"rule-based":[108],"and":[110,130,157,169,202,222,246],"user":[112],"simulator":[113],"communicating":[114],"dialog-act":[117],"level,":[118],"crowdsource":[120],"surface":[122],"sentences":[123],"authoring":[124],"both":[126,179],"simulated":[128,162],"users":[129],"agent,":[132],"which":[133],"allow":[134],"generate":[137],"dataset":[139],"interactions":[141,151],"in":[142],"natural":[143],"language.":[144],"Then,":[145],"annotate":[147],"each":[148],"these":[150],"with":[152],"rapport":[155,175],"score":[156],"analyze":[158],"links":[160],"between":[161],"users'":[163,241,263],"goals,":[165],"policies,":[168],"Our":[171],"results":[172,252],"show":[173,253],"was":[176],"higher":[177],"or":[180],"none":[181],"interlocutors":[184],"We":[189,225],"use":[190],"result":[192],"inform":[194],"design":[196],"social":[199,207],"reward":[200,208],"function,":[201],"rely":[204],"function":[209],"train":[211],"an":[216,255],"hybrid":[217],"approach":[218,228],"supervised":[220],"learning":[221],"reinforcement":[223],"learning.":[224],"evaluate":[226],"our":[227,235],"by":[229],"comparing":[230],"two":[231],"different":[232],"versions":[233],"agent:":[237],"takes":[240],"goals":[243,265],"into":[244],"account":[245],"another":[247],"does":[249],"not.":[250],"The":[251],"adapting":[257],"performs":[266],"better.":[267]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}