{"id":"https://openalex.org/W3104546989","doi":"https://doi.org/10.18653/v1/d17-1237","title":"Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning","display_name":"Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W3104546989","doi":"https://doi.org/10.18653/v1/d17-1237","mag":"3104546989"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1237","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1237","pdf_url":"https://www.aclweb.org/anthology/D17-1237.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1237.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066404470","display_name":"Baolin Peng","orcid":"https://orcid.org/0009-0004-3255-8735"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baolin Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101542195","display_name":"Xiujun Li","orcid":"https://orcid.org/0000-0002-0849-4637"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Xiujun Li","raw_affiliation_strings":["? The Chinese University of Hong Kong, Hong Kong","Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"? The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107006279","display_name":"Lihong Li","orcid":"https://orcid.org/0000-0002-1264-8483"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lihong Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["? The Chinese University of Hong Kong, Hong Kong","Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"? The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030468199","display_name":"Asl\u0131 \u00c7eliky\u0131lmaz","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Asli Celikyilmaz","raw_affiliation_strings":["? The Chinese University of Hong Kong, Hong Kong","Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"? The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720086","display_name":"Sung\u2010Jin Lee","orcid":"https://orcid.org/0000-0001-9348-8356"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK","US"],"is_corresponding":false,"raw_author_name":"Sungjin Lee","raw_affiliation_strings":["? The Chinese University of Hong Kong, Hong Kong","Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"? The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008208316","display_name":"Kam\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-9427-5659"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK","US"],"is_corresponding":true,"raw_author_name":"Kam-Fai Wong","raw_affiliation_strings":["? The Chinese University of Hong Kong, Hong Kong","Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"? The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008208316"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":156,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.9994999766349792,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9969000220298767,"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":0.9474283456802368},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7868508696556091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7778381109237671},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7279019951820374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6244673132896423},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.43465322256088257},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41217565536499023},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3978232741355896},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0975508987903595}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9474283456802368},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7868508696556091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7778381109237671},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7279019951820374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6244673132896423},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.43465322256088257},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41217565536499023},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3978232741355896},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0975508987903595},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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:10.18653/v1/d17-1237","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1237","pdf_url":"https://www.aclweb.org/anthology/D17-1237.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1237","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1237","pdf_url":"https://www.aclweb.org/anthology/D17-1237.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3104546989.pdf","grobid_xml":"https://content.openalex.org/works/W3104546989.grobid-xml"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W16046748","https://openalex.org/W137851535","https://openalex.org/W638006253","https://openalex.org/W1489525520","https://openalex.org/W1492935830","https://openalex.org/W1494114146","https://openalex.org/W1552182777","https://openalex.org/W1584761227","https://openalex.org/W1592847719","https://openalex.org/W1700691926","https://openalex.org/W1763968285","https://openalex.org/W1948566616","https://openalex.org/W1956340063","https://openalex.org/W1975244201","https://openalex.org/W1982897610","https://openalex.org/W2021618504","https://openalex.org/W2024632416","https://openalex.org/W2062175565","https://openalex.org/W2062295023","https://openalex.org/W2078745840","https://openalex.org/W2078861931","https://openalex.org/W2098651115","https://openalex.org/W2107587102","https://openalex.org/W2109910161","https://openalex.org/W2118462278","https://openalex.org/W2120045257","https://openalex.org/W2121325257","https://openalex.org/W2121517924","https://openalex.org/W2123891489","https://openalex.org/W2128856065","https://openalex.org/W2132997613","https://openalex.org/W2145339207","https://openalex.org/W2149327368","https://openalex.org/W2154652894","https://openalex.org/W2158548602","https://openalex.org/W2161181481","https://openalex.org/W2164777277","https://openalex.org/W2204900930","https://openalex.org/W2250530145","https://openalex.org/W2251165062","https://openalex.org/W2251251208","https://openalex.org/W2251291469","https://openalex.org/W2251818274","https://openalex.org/W2291723583","https://openalex.org/W2294065713","https://openalex.org/W2417401578","https://openalex.org/W2427764808","https://openalex.org/W2473329891","https://openalex.org/W2483402000","https://openalex.org/W2512152365","https://openalex.org/W2518570122","https://openalex.org/W2530291685","https://openalex.org/W2558661633","https://openalex.org/W2564590796","https://openalex.org/W2571927164","https://openalex.org/W2578330760","https://openalex.org/W2594726847","https://openalex.org/W2604688337","https://openalex.org/W2745039414","https://openalex.org/W2949252816","https://openalex.org/W2951577137","https://openalex.org/W2962682659","https://openalex.org/W2963068985","https://openalex.org/W2963262099","https://openalex.org/W2963503801","https://openalex.org/W2963903950","https://openalex.org/W2963912046","https://openalex.org/W4302353911"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2379651310"],"abstract_inverted_index":{"Building":[0],"a":[1,32,36,73,81,96,107,126,140],"dialogue":[2,82,91,98,109],"agent":[3,16,28],"to":[4,18,20,30,79,115,154],"fulfill":[5],"complex":[6],"tasks,":[7],"such":[8],"as":[9],"travel":[10,141],"planning,":[11],"is":[12],"challenging":[13],"because":[14],"the":[15,27,58,61,117,121,166],"has":[17],"learn":[19],"collectively":[21],"complete":[22,116],"multiple":[23],"subtasks.":[24],"For":[25],"example,":[26],"needs":[29],"reserve":[31],"hotel":[33,49],"and":[34,48,71,124,146,165],"book":[35],"flight":[37],"so":[38],"that":[39,84,100,111,130,150],"there":[40],"leaves":[41],"enough":[42],"time":[43],"for":[44],"commute":[45],"between":[46],"arrival":[47],"check-in.":[50],"This":[51],"paper":[52],"addresses":[53],"this":[54],"challenge":[55],"by":[56,120],"formulating":[57],"task":[59,143],"in":[60],"mathematical":[62],"framework":[63],"of":[64],"options":[65],"over":[66,157],"Markov":[67],"Decision":[68],"Processes":[69],"(MDPs),":[70],"proposing":[72],"hierarchical":[74],"deep":[75,171],"reinforcement":[76,172],"learning":[77,80],"approach":[78,152],"manager":[83,92],"operates":[85],"at":[86],"different":[87],"temporal":[88],"scales.":[89],"The":[90],"consists":[93],"of:":[94],"(1)":[95],"top-level":[97,122],"policy":[99,110],"selects":[101,112],"among":[102],"subtasks":[103],"or":[104],"options,":[105],"(2)":[106],"low-level":[108],"primitive":[113],"actions":[114],"subtask":[118],"given":[119],"policy,":[123],"(3)":[125],"global":[127],"state":[128],"tracker":[129],"helps":[131],"ensure":[132],"all":[133],"cross-subtask":[134],"constraints":[135],"be":[136],"satisfied.":[137],"Experiments":[138],"on":[139,162,169],"planning":[142],"with":[144],"simulated":[145],"real":[147],"users":[148],"show":[149],"our":[151],"leads":[153],"significant":[155],"improvements":[156],"three":[158],"baselines,":[159],"two":[160],"based":[161,168],"handcrafted":[163],"rules":[164],"other":[167],"flat":[170],"learning.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":40},{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":18}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-11-23T00:00:00"}