{"id":"https://openalex.org/W2798494119","doi":"https://doi.org/10.18653/v1/p18-1203","title":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning","display_name":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2798494119","doi":"https://doi.org/10.18653/v1/p18-1203","mag":"2798494119"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p18-1203","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1203","pdf_url":"https://www.aclweb.org/anthology/P18-1203.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P18-1203.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":true,"raw_author_name":"Baolin Peng","raw_affiliation_strings":[],"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/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"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"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xiujun Li","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"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/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"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"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100627504","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-3163-3420"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]},{"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"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Jingjing Liu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"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/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kam-Fai Wong","raw_affiliation_strings":["MoE Key Lab of High Confidence Software Technologies, China"],"affiliations":[{"raw_affiliation_string":"MoE Key Lab of High Confidence Software Technologies, China","institution_ids":["https://openalex.org/I4210128818"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5066404470"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.0441,"has_fulltext":true,"cited_by_count":185,"citation_normalized_percentile":{"value":0.99229473,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2182","last_page":"2192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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"}},"topics":[{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","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/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8289638161659241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8177902698516846},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.740166425704956},{"id":"https://openalex.org/keywords/ticket","display_name":"Ticket","score":0.670899510383606},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.6026819944381714},{"id":"https://openalex.org/keywords/user-modeling","display_name":"User modeling","score":0.45286035537719727},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4388328790664673},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.43507930636405945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4244641661643982},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.21703431010246277},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15845796465873718},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11154705286026001},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09095326066017151}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8289638161659241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8177902698516846},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.740166425704956},{"id":"https://openalex.org/C2776540713","wikidata":"https://www.wikidata.org/wiki/Q7800647","display_name":"Ticket","level":2,"score":0.670899510383606},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6026819944381714},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.45286035537719727},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4388328790664673},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.43507930636405945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4244641661643982},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.21703431010246277},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15845796465873718},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11154705286026001},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09095326066017151},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p18-1203","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1203","pdf_url":"https://www.aclweb.org/anthology/P18-1203.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p18-1203","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p18-1203","pdf_url":"https://www.aclweb.org/anthology/P18-1203.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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320326427","display_name":"Innovation and Technology Fund","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2798494119.pdf","grobid_xml":"https://content.openalex.org/works/W2798494119.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W16046748","https://openalex.org/W52170320","https://openalex.org/W1491843047","https://openalex.org/W1515851193","https://openalex.org/W1564312725","https://openalex.org/W1681299129","https://openalex.org/W1758031947","https://openalex.org/W1778387566","https://openalex.org/W1948566616","https://openalex.org/W1975244201","https://openalex.org/W2035934535","https://openalex.org/W2048226872","https://openalex.org/W2062175565","https://openalex.org/W2109038907","https://openalex.org/W2112483970","https://openalex.org/W2117989772","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2290354866","https://openalex.org/W2295072214","https://openalex.org/W2396229782","https://openalex.org/W2412899141","https://openalex.org/W2417401578","https://openalex.org/W2473329891","https://openalex.org/W2507592741","https://openalex.org/W2567374473","https://openalex.org/W2571927164","https://openalex.org/W2594726847","https://openalex.org/W2765111838","https://openalex.org/W2766447205","https://openalex.org/W2949252816","https://openalex.org/W2950314731","https://openalex.org/W2950471160","https://openalex.org/W2950517718","https://openalex.org/W2962776342","https://openalex.org/W2962996309","https://openalex.org/W2963043030","https://openalex.org/W2963064439","https://openalex.org/W2963068985","https://openalex.org/W2964077562","https://openalex.org/W2964080167","https://openalex.org/W2964101860","https://openalex.org/W3021208093","https://openalex.org/W3104546989","https://openalex.org/W4229706854","https://openalex.org/W4245108548","https://openalex.org/W4293396018"],"related_works":["https://openalex.org/W132856376","https://openalex.org/W4288388931","https://openalex.org/W2892636954","https://openalex.org/W4206805925","https://openalex.org/W4375841483","https://openalex.org/W2022874741","https://openalex.org/W2364431604","https://openalex.org/W2018860124","https://openalex.org/W3112526189","https://openalex.org/W2572886659"],"abstract_inverted_index":{"Training":[0],"a":[1,25,29,84,146],"task-completion":[2,74],"dialogue":[3,75,82,105,127],"agent":[4,83,128],"via":[5],"reinforcement":[6],"learning":[7],"(RL)":[8],"is":[9,22,64,111,129,143],"costly":[10],"because":[11],"it":[12],"requires":[13],"many":[14],"interactions":[15],"with":[16,114],"real":[17,97,115,120,133],"users.":[18],"One":[19],"common":[20],"alternative":[21],"to":[23,48,61,90,95,118],"use":[24],"user":[26,30,98,116,121],"simulator.":[27],"However,":[28],"simulator":[31],"usually":[32],"lacks":[33],"the":[34,41,50,65,81,87,92,108,126],"language":[35],"complexity":[36],"of":[37,86,140],"human":[38],"interlocutors":[39],"and":[40,100,123,135,153],"biases":[42],"in":[43,124,150],"its":[44],"design":[45],"may":[46],"tend":[47],"degrade":[49],"agent.":[51],"To":[52],"address":[53],"these":[54],"issues,":[55],"we":[56],"present":[57],"Deep":[58],"Dyna-Q,":[59],"which":[60],"our":[62,141],"knowledge":[63],"first":[66],"deep":[67],"RL":[68],"framework":[69],"that":[70],"integrates":[71],"planning":[72],"for":[73],"policy":[76,106],"learning.":[77],"We":[78],"incorporate":[79],"into":[80],"model":[85,110],"environment,":[88],"referred":[89],"as":[91],"world":[93,109],"model,":[94],"mimic":[96],"response":[99],"generate":[101],"simulated":[102,136,152],"experience.":[103,137],"During":[104],"learning,":[107],"constantly":[112],"updated":[113],"experience":[117,134],"approach":[119,142],"behavior,":[122],"turn,":[125],"optimized":[130],"using":[131],"both":[132,151],"The":[138],"effectiveness":[139],"demonstrated":[144],"on":[145],"movie-ticket":[147],"booking":[148],"task":[149],"human-in-theloop":[154],"settings":[155],"1":[156],".":[157]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":25},{"year":2021,"cited_by_count":32},{"year":2020,"cited_by_count":46},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}