{"id":"https://openalex.org/W2765111838","doi":"https://doi.org/10.1109/icassp.2018.8461918","title":"Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning","display_name":"Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2765111838","doi":"https://doi.org/10.1109/icassp.2018.8461918","mag":"2765111838"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066404470","display_name":"Baolin Peng","orcid":"https://orcid.org/0009-0004-3255-8735"},"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"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Baolin Peng","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"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/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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiujun Li","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"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/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingjing Liu","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076610826","display_name":"Yun-Nung Chen","orcid":"https://orcid.org/0000-0003-1777-3942"},"institutions":[{"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"],"is_corresponding":false,"raw_author_name":"Yun-Nung Chen","raw_affiliation_strings":["National Taiwan University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"National Taiwan University, Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"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/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kam-Fai Wong","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5066404470"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":6.0267,"has_fulltext":false,"cited_by_count":70,"citation_normalized_percentile":{"value":0.96957536,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6149","last_page":"6153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9991000294685364,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9966999888420105,"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/adversarial-system","display_name":"Adversarial system","score":0.9342231750488281},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.8832744359970093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7952876091003418},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6335176229476929},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5792598128318787},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5756555795669556},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5014512538909912},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.49132266640663147},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.4424998164176941},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4225907325744629},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3621777296066284},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09303662180900574},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.080942302942276}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9342231750488281},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.8832744359970093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7952876091003418},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6335176229476929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5792598128318787},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5756555795669556},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5014512538909912},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.49132266640663147},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.4424998164176941},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4225907325744629},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3621777296066284},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09303662180900574},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.080942302942276},{"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1786470251","https://openalex.org/W1975244201","https://openalex.org/W1999874108","https://openalex.org/W2119717200","https://openalex.org/W2139612737","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2417401578","https://openalex.org/W2417786368","https://openalex.org/W2571927164","https://openalex.org/W2594726847","https://openalex.org/W2766447205","https://openalex.org/W2783543950","https://openalex.org/W2949252816","https://openalex.org/W2950872548","https://openalex.org/W2962730405","https://openalex.org/W2962776342","https://openalex.org/W2963043030","https://openalex.org/W2963068985","https://openalex.org/W2963277051","https://openalex.org/W2964043796","https://openalex.org/W3104546989","https://openalex.org/W4296240856","https://openalex.org/W4320013936","https://openalex.org/W6638467422","https://openalex.org/W6650265722","https://openalex.org/W6685757253","https://openalex.org/W6692846177","https://openalex.org/W6715753392","https://openalex.org/W6716474083","https://openalex.org/W6718092244","https://openalex.org/W6734696739","https://openalex.org/W6747812028","https://openalex.org/W6764397996"],"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/W2995777218"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,33,85],"new":[4],"method":[5],"-":[6],"adversarial":[7,28],"advantage":[8,56],"actor-critic":[9,57],"(Adversarial":[10],"A2C),":[11],"which":[12],"significantly":[13],"improves":[14],"the":[15,49,55,62,69,72,80,91],"efficiency":[16],"of":[17,79],"dialogue":[18,23,40,63],"policy":[19,97],"learning":[20],"in":[21,84],"task-completion":[22],"systems.":[24],"Inspired":[25],"by":[26,39,44],"generative":[27],"networks":[29],"(GAN),":[30],"we":[31,47],"train":[32],"discriminator":[34,50],"to":[35,60,65,77],"differentiate":[36],"responses/actions":[37,43],"generated":[38],"agents":[41],"from":[42],"experts.":[45,81],"Then,":[46],"incorporate":[48],"as":[51],"another":[52],"critic":[53],"into":[54],"(A2C)":[58],"framework,":[59],"encourage":[61],"agent":[64,73],"explore":[66],"state-action":[67],"within":[68],"regions":[70],"where":[71],"takes":[74],"actions":[75],"similar":[76],"those":[78],"Experimental":[82],"results":[83],"movie-ticket":[86],"booking":[87],"domain":[88],"show":[89],"that":[90],"proposed":[92],"Adversarial":[93],"A2C":[94],"can":[95],"accelerate":[96],"exploration":[98],"efficiently.":[99]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":12},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}