{"id":"https://openalex.org/W2759104452","doi":"https://doi.org/10.18653/v1/d17-1260","title":"Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning","display_name":"Agent-Aware Dropout DQN for Safe and Efficient On-line Dialogue Policy Learning","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2759104452","doi":"https://doi.org/10.18653/v1/d17-1260","mag":"2759104452"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1260","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1260","pdf_url":"https://www.aclweb.org/anthology/D17-1260.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 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/D17-1260.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100432073","display_name":"Lu Chen","orcid":"https://orcid.org/0000-0002-1186-3544"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210165726","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165456","https://openalex.org/I4210165726"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab, Department of Computer Science and Engineering Brain Science and Technology Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab, Department of Computer Science and Engineering Brain Science and Technology Research Center","institution_ids":["https://openalex.org/I4210165726"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030761097","display_name":"Xiang Zhou","orcid":"https://orcid.org/0000-0002-3835-3894"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210165726","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165456","https://openalex.org/I4210165726"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Zhou","raw_affiliation_strings":["Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab, Department of Computer Science and Engineering Brain Science and Technology Research Center","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab, Department of Computer Science and Engineering Brain Science and Technology Research Center","institution_ids":["https://openalex.org/I4210165726"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101987170","display_name":"Cheng Chang","orcid":"https://orcid.org/0000-0001-6589-4437"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210165726","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165456","https://openalex.org/I4210165726"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Chang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China","Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab, Department of Computer Science and Engineering Brain Science and Technology Research Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab, Department of Computer Science and Engineering Brain Science and Technology Research Center","institution_ids":["https://openalex.org/I4210165726"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032223753","display_name":"Runzhe Yang","orcid":"https://orcid.org/0000-0001-8891-5149"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210165726","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165456","https://openalex.org/I4210165726"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runzhe Yang","raw_affiliation_strings":["Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab, Department of Computer Science and Engineering Brain Science and Technology Research Center","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab, Department of Computer Science and Engineering Brain Science and Technology Research Center","institution_ids":["https://openalex.org/I4210165726"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I4210165726","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210165456","https://openalex.org/I4210165726"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab, Department of Computer Science and Engineering Brain Science and Technology Research Center","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Eng. SpeechLab, Department of Computer Science and Engineering Brain Science and Technology Research Center","institution_ids":["https://openalex.org/I4210165726"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2454","last_page":"2464"},"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":0.9994999766349792,"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":0.996399998664856,"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/dropout","display_name":"Dropout (neural networks)","score":0.8936172723770142},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8851180672645569},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8013354539871216},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.5882854461669922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5720430612564087},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4862450659275055},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.4854336380958557},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4499814808368683}],"concepts":[{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.8936172723770142},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8851180672645569},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8013354539871216},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.5882854461669922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5720430612564087},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4862450659275055},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.4854336380958557},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4499814808368683},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/d17-1260","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1260","pdf_url":"https://www.aclweb.org/anthology/D17-1260.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 Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1260","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1260","pdf_url":"https://www.aclweb.org/anthology/D17-1260.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 Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2368558818","display_name":null,"funder_award_id":"61603252","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5039175848","display_name":null,"funder_award_id":"61573241","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6460810127","display_name":null,"funder_award_id":"14JCZ03","funder_id":"https://openalex.org/F4320322999","funder_display_name":"Shanghai Jiao Tong University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2759104452.pdf","grobid_xml":"https://content.openalex.org/works/W2759104452.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W52170320","https://openalex.org/W99537330","https://openalex.org/W582134693","https://openalex.org/W1595483645","https://openalex.org/W1757796397","https://openalex.org/W1778387566","https://openalex.org/W1904365287","https://openalex.org/W1975244201","https://openalex.org/W2021151961","https://openalex.org/W2035934535","https://openalex.org/W2047335008","https://openalex.org/W2062175565","https://openalex.org/W2095705004","https://openalex.org/W2115101920","https://openalex.org/W2122250135","https://openalex.org/W2126810476","https://openalex.org/W2145339207","https://openalex.org/W2157797701","https://openalex.org/W2164411961","https://openalex.org/W2166550727","https://openalex.org/W2168359464","https://openalex.org/W2175723363","https://openalex.org/W2251058040","https://openalex.org/W2257979135","https://openalex.org/W2280163991","https://openalex.org/W2408200822","https://openalex.org/W2417401578","https://openalex.org/W2438667436","https://openalex.org/W2507592741","https://openalex.org/W2594726847","https://openalex.org/W2740191615","https://openalex.org/W2962776342","https://openalex.org/W2962996309","https://openalex.org/W2963938771","https://openalex.org/W2963993502","https://openalex.org/W2963993719","https://openalex.org/W2964044380","https://openalex.org/W2964059111","https://openalex.org/W4298857966"],"related_works":["https://openalex.org/W3082178636","https://openalex.org/W178231042","https://openalex.org/W2360028903","https://openalex.org/W4280543773","https://openalex.org/W2366083136","https://openalex.org/W1521968289","https://openalex.org/W2387622493","https://openalex.org/W2782041652","https://openalex.org/W2952088488","https://openalex.org/W1932132538"],"abstract_inverted_index":{"Hand-crafted":[0],"rules":[1],"and":[2,66,100,122,136,150],"reinforcement":[3],"learning":[4,44,160],"(RL)":[5],"are":[6],"two":[7,49,116],"popular":[8],"choices":[9],"to":[10,46,90,96,102,130,157],"obtain":[11],"dialogue":[12,53,169],"policy.":[13],"The":[14],"rule-based":[15,60],"policy":[16,54,61,154],"is":[17,28,88],"often":[18,33],"reliable":[19],"within":[20],"predefined":[21,59],"scope":[22],"but":[23,32],"not":[24],"self-adaptable,":[25],"whereas":[26],"RL":[27,70],"evolvable":[29],"with":[30],"data":[31],"suffers":[34],"from":[35,104],"a":[36,42,58,64,68,110],"bad":[37],"initial":[38],"performance.":[39],"We":[40],"employ":[41],"companion":[43,159],"framework":[45],"integrate":[47],"the":[48,92,98,105,132,142],"approaches":[50,161],"for":[51,120],"on-line":[52,153],"learning,":[55],"in":[56],"which":[57],"acts":[62],"as":[63,76,78,109,162,164],"teacher":[65,99],"guides":[67],"data-driven":[69,111],"system":[71],"by":[72,128],"giving":[73],"example":[74],"actions":[75],"well":[77,163],"additional":[79],"rewards.":[80],"A":[81],"novel":[82],"agent-aware":[83],"dropout":[84,129],"Deep":[85],"Q-Network":[86],"(AAD-DQN)":[87],"proposed":[89,143],"address":[91],"problem":[93],"of":[94,134,152],"when":[95],"consult":[97],"how":[101],"learn":[103],"teacher's":[106],"experiences.":[107],"AAD-DQN,":[108],"student":[112,121],"policy,":[113],"provides":[114],"(1)":[115],"separate":[117],"experience":[118],"memories":[119],"teacher,":[123],"(2)":[124],"an":[125],"uncertainty":[126],"estimated":[127],"control":[131],"timing":[133],"consultation":[135],"learning.":[137],"Simulation":[138],"experiments":[139],"showed":[140],"that":[141],"approach":[144],"can":[145],"significantly":[146],"improve":[147],"both":[148],"safety":[149],"efficiency":[151],"optimization":[155],"compared":[156],"other":[158],"supervised":[165],"pre-training":[166],"using":[167],"static":[168],"corpus.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":7}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}