{"id":"https://openalex.org/W2965568842","doi":"https://doi.org/10.1145/3350546.3352501","title":"Reinforcement Learning for Personalized Dialogue Management","display_name":"Reinforcement Learning for Personalized Dialogue Management","publication_year":2019,"publication_date":"2019-10-14","ids":{"openalex":"https://openalex.org/W2965568842","doi":"https://doi.org/10.1145/3350546.3352501","mag":"2965568842"},"language":"en","primary_location":{"id":"doi:10.1145/3350546.3352501","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3350546.3352501","pdf_url":null,"source":{"id":"https://openalex.org/S4363608074","display_name":"IEEE/WIC/ACM International Conference on Web Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC/ACM International Conference on Web Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3350546.3352501","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082645091","display_name":"Floris den Hengst","orcid":"https://orcid.org/0000-0002-2092-9904"},"institutions":[{"id":"https://openalex.org/I4210148881","display_name":"ING Bank","ror":"https://ror.org/059et9981","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210148881"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Floris den Hengst","raw_affiliation_strings":["ING Group N.V., Netherlands"],"affiliations":[{"raw_affiliation_string":"ING Group N.V., Netherlands","institution_ids":["https://openalex.org/I4210148881"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044217809","display_name":"Mark Hoogendoorn","orcid":"https://orcid.org/0000-0003-3356-3574"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mark Hoogendoorn","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Netherlands","Vrije Universiteit, Amsterdam (Netherlands)"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]},{"raw_affiliation_string":"Vrije Universiteit, Amsterdam (Netherlands)","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029130731","display_name":"Frank van Harmelen","orcid":"https://orcid.org/0000-0002-7913-0048"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Frank van Harmelen","raw_affiliation_strings":["Vrije Universiteit Amsterdam, Netherlands","Vrije Universiteit, Amsterdam (Netherlands)"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]},{"raw_affiliation_string":"Vrije Universiteit, Amsterdam (Netherlands)","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035991190","display_name":"Joost Bosman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148881","display_name":"ING Bank","ror":"https://ror.org/059et9981","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210148881"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Joost Bosman","raw_affiliation_strings":["ING Group N.V., Netherlands"],"affiliations":[{"raw_affiliation_string":"ING Group N.V., Netherlands","institution_ids":["https://openalex.org/I4210148881"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5082645091"],"corresponding_institution_ids":["https://openalex.org/I4210148881"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.09822785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"67"},"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":0.9986000061035156,"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":0.9975000023841858,"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":0.8832186460494995},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.815213680267334},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.7257378101348877},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.7032743096351624},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6060996055603027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4922892153263092},{"id":"https://openalex.org/keywords/product","display_name":"Product (mathematics)","score":0.4772767424583435},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4290134906768799},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3349311947822571},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32822781801223755},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3097548484802246}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8832186460494995},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.815213680267334},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.7257378101348877},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7032743096351624},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6060996055603027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4922892153263092},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4772767424583435},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4290134906768799},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3349311947822571},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32822781801223755},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3097548484802246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3350546.3352501","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3350546.3352501","pdf_url":null,"source":{"id":"https://openalex.org/S4363608074","display_name":"IEEE/WIC/ACM International Conference on Web Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC/ACM International Conference on Web Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1908.00286","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1908.00286","pdf_url":"https://arxiv.org/pdf/1908.00286","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"doi:10.48550/arxiv.1908.00286","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1908.00286","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:2965568842","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"doi:10.1145/3350546.3352501","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3350546.3352501","pdf_url":null,"source":{"id":"https://openalex.org/S4363608074","display_name":"IEEE/WIC/ACM International Conference on Web Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/WIC/ACM International Conference on Web Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W305620562","https://openalex.org/W587977456","https://openalex.org/W1133916940","https://openalex.org/W1530276735","https://openalex.org/W1542026696","https://openalex.org/W1552548559","https://openalex.org/W1560147776","https://openalex.org/W1654805921","https://openalex.org/W1778387566","https://openalex.org/W1975244201","https://openalex.org/W2001771035","https://openalex.org/W2007221309","https://openalex.org/W2032282529","https://openalex.org/W2044712489","https://openalex.org/W2046831886","https://openalex.org/W2056089161","https://openalex.org/W2062175565","https://openalex.org/W2102937240","https://openalex.org/W2112420033","https://openalex.org/W2145482038","https://openalex.org/W2152883745","https://openalex.org/W2155968351","https://openalex.org/W2250558341","https://openalex.org/W2251058040","https://openalex.org/W2251235149","https://openalex.org/W2396553719","https://openalex.org/W2407709678","https://openalex.org/W2438667436","https://openalex.org/W2735575534","https://openalex.org/W2746553466","https://openalex.org/W2772217324","https://openalex.org/W2781726626","https://openalex.org/W2962902376","https://openalex.org/W2963560082","https://openalex.org/W2963993502","https://openalex.org/W2964044380","https://openalex.org/W2964309167","https://openalex.org/W6633543148","https://openalex.org/W6691246603","https://openalex.org/W6746188011"],"related_works":["https://openalex.org/W2980520305","https://openalex.org/W1564312725","https://openalex.org/W2998033461","https://openalex.org/W1982869221","https://openalex.org/W101646624","https://openalex.org/W3015197516","https://openalex.org/W2519349389","https://openalex.org/W2903826588","https://openalex.org/W2997193124","https://openalex.org/W2162265730","https://openalex.org/W2891447705","https://openalex.org/W2141839844","https://openalex.org/W3005560120","https://openalex.org/W2968937098","https://openalex.org/W2332917788","https://openalex.org/W3111212392","https://openalex.org/W3206497389","https://openalex.org/W2186554646","https://openalex.org/W2246091503","https://openalex.org/W3166533872"],"abstract_inverted_index":{"Language":[0],"systems":[1],"have":[2,12,32,39],"been":[3,41],"of":[4,54,81,94,121,152,166,174],"great":[5],"interest":[6],"to":[7,63,65,105],"the":[8,15,23,47,51,79,117,128,172],"research":[9],"community":[10],"and":[11,38,75,98,115,138,155,161,176,181],"recently":[13,40],"reached":[14],"mass":[16],"market":[17],"through":[18],"various":[19],"assistant":[20],"platforms":[21],"on":[22,179],"web.":[24],"Reinforcement":[25,101],"Learning":[26,102],"methods":[27,44,157],"that":[28,45,126,183],"optimize":[29],"dialogue":[30,122],"policies":[31],"seen":[33],"successes":[34],"in":[35,149,158],"past":[36],"years":[37],"extended":[42],"into":[43,56],"personalize":[46],"dialogue,":[48],"e.g.":[49],"take":[50],"personal":[52],"context":[53,82,95,137,175],"users":[55,135],"account.":[57],"These":[58],"works,":[59],"however,":[60],"are":[61],"limited":[62],"personalization":[64],"a":[66,88,91,112,141,150,188],"single":[67,113],"user":[68,129],"with":[69,124],"whom":[70],"they":[71],"require":[72],"multiple":[73],"interactions":[74],"do":[76],"not":[77],"generalize":[78],"usage":[80,93],"across":[83],"users.":[84],"This":[85],"work":[86],"introduces":[87],"problem":[89],"where":[90],"generalized":[92],"is":[96],"relevant":[97],"proposes":[99],"two":[100],"(RL)-based":[103],"approaches":[104,148,185],"this":[106],"problem.":[107],"The":[108,131],"first":[109],"approach":[110,133],"uses":[111],"learner":[114,142],"extends":[116],"traditional":[118],"POMDP":[119],"formulation":[120],"state":[123],"features":[125],"describe":[127],"context.":[130,144],"second":[132],"segments":[134],"by":[136],"then":[139],"employs":[140],"per":[143],"We":[145,170],"compare":[146,171],"these":[147],"benchmark":[151],"existing":[153],"non-RL":[154],"RL-based":[156],"three":[159],"established":[160],"one":[162],"novel":[163],"application":[164],"domain":[165],"financial":[167],"product":[168],"recommendation.":[169],"influence":[173],"training":[177],"experiences":[178],"performance":[180],"find":[182],"learning":[184],"generally":[186],"outperform":[187],"handcrafted":[189],"gold":[190],"standard.":[191]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}