{"id":"https://openalex.org/W2889186204","doi":"https://doi.org/10.18653/v1/d18-1416","title":"Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning","display_name":"Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2889186204","doi":"https://doi.org/10.18653/v1/d18-1416","mag":"2889186204"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d18-1416","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1416","pdf_url":"https://www.aclweb.org/anthology/D18-1416.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D18-1416.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077356556","display_name":"Shang\u2010Yu Su","orcid":"https://orcid.org/0000-0003-4313-6066"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang-Yu Su","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/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/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Xiujun Li","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"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/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW","US"],"is_corresponding":true,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100442542","display_name":"Jingjing Liu","orcid":"https://orcid.org/0009-0002-6277-5816"},"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/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW","US"],"is_corresponding":false,"raw_author_name":"Jingjing Liu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA","National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076610826","display_name":"Yun-Nung Chen","orcid":"https://orcid.org/0000-0003-1777-3942"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun-Nung Chen","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5114910293"],"corresponding_institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I16733864"],"apc_list":null,"apc_paid":null,"fwci":9.4774,"has_fulltext":true,"cited_by_count":74,"citation_normalized_percentile":{"value":0.98311504,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3813","last_page":"3823"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9993000030517578,"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":0.9955000281333923,"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/robustness","display_name":"Robustness (evolution)","score":0.8354834318161011},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8232865333557129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7619365453720093},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6396766901016235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6212525963783264},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4998607635498047},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46864742040634155}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8354834318161011},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8232865333557129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7619365453720093},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6396766901016235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6212525963783264},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4998607635498047},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46864742040634155},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d18-1416","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1416","pdf_url":"https://www.aclweb.org/anthology/D18-1416.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d18-1416","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d18-1416","pdf_url":"https://www.aclweb.org/anthology/D18-1416.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 2018 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7900000214576721}],"awards":[{"id":"https://openalex.org/G7160539585","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322410","display_name":"MediaTek","ror":"https://ror.org/05g9jck81"},{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2889186204.pdf","grobid_xml":"https://content.openalex.org/works/W2889186204.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1491843047","https://openalex.org/W1948566616","https://openalex.org/W1975244201","https://openalex.org/W2062175565","https://openalex.org/W2109038907","https://openalex.org/W2117989772","https://openalex.org/W2145339207","https://openalex.org/W2290354866","https://openalex.org/W2295072214","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/W2783543950","https://openalex.org/W2949252816","https://openalex.org/W2950471160","https://openalex.org/W2962776342","https://openalex.org/W2962996309","https://openalex.org/W2963043030","https://openalex.org/W2963068985","https://openalex.org/W2963140401","https://openalex.org/W2963797754","https://openalex.org/W2964077562","https://openalex.org/W2964080167","https://openalex.org/W2964101860","https://openalex.org/W2964210218","https://openalex.org/W3021208093","https://openalex.org/W3104546989","https://openalex.org/W4293396018","https://openalex.org/W4295249402"],"related_works":["https://openalex.org/W4293202849","https://openalex.org/W1980965563","https://openalex.org/W1489300767","https://openalex.org/W4380714744","https://openalex.org/W2387995142","https://openalex.org/W4319453655","https://openalex.org/W2089959425","https://openalex.org/W2964074194","https://openalex.org/W2057775761","https://openalex.org/W4380075502"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,19,98,109],"Discriminative":[4],"Deep":[5,16],"Dyna-Q":[6,17,26],"(D3Q)":[7],"approach":[8],"to":[9,28,54,64,108],"improving":[10],"the":[11,25,42,66,80,103],"effectiveness":[12,89],"and":[13,90],"robustness":[14,91],"of":[15,44,68,82,92,106],"(DDQ),":[18],"recently":[20],"proposed":[21],"framework":[22],"that":[23,73],"extends":[24],"algorithm":[27],"integrate":[29],"planning":[30],"for":[31,86],"task-completion":[32],"dialogue":[33],"policy":[34],"learning.":[35],"To":[36],"obviate":[37],"DDQ's":[38],"high":[39],"dependency":[40],"on":[41],"quality":[43,67,81],"simulated":[45,56,83],"experiences,":[46],"we":[47],"incorporate":[48],"an":[49],"RNN-based":[50],"discriminator":[51],"in":[52,62,97],"D3Q":[53,74,93],"differentiate":[55],"experience":[57,61,84],"from":[58],"real":[59],"user":[60],"order":[63],"control":[65],"training":[69],"data.":[70],"Experiments":[71],"show":[72],"significantly":[75],"outperforms":[76],"DDQ":[77],"by":[78],"controlling":[79],"used":[85],"planning.":[87],"The":[88],"is":[94,112],"further":[95],"demonstrated":[96],"domain":[99],"extension":[100],"setting,":[101],"where":[102],"agent's":[104],"capability":[105],"adapting":[107],"changing":[110],"environment":[111],"tested.":[113],"1":[114]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":26},{"year":2019,"cited_by_count":13}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}