{"id":"https://openalex.org/W3133451788","doi":"https://doi.org/10.1109/tcds.2021.3061121","title":"Efficient Dialog Policy Learning With Hindsight, User Modeling, and Adaptation","display_name":"Efficient Dialog Policy Learning With Hindsight, User Modeling, and Adaptation","publication_year":2021,"publication_date":"2021-02-23","ids":{"openalex":"https://openalex.org/W3133451788","doi":"https://doi.org/10.1109/tcds.2021.3061121","mag":"3133451788"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2021.3061121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2021.3061121","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-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/A5023163708","display_name":"Keting Lu","orcid":"https://orcid.org/0000-0002-4844-5792"},"institutions":[{"id":"https://openalex.org/I98301712","display_name":"Baidu (China)","ror":"https://ror.org/03vs3wt56","country_code":"CN","type":"company","lineage":["https://openalex.org/I98301712"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keting Lu","raw_affiliation_strings":["Commercialization Recommending Researching Department, Baidu Inc., Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4844-5792","affiliations":[{"raw_affiliation_string":"Commercialization Recommending Researching Department, Baidu Inc., Shanghai, China","institution_ids":["https://openalex.org/I98301712"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101935217","display_name":"Yan Cao","orcid":"https://orcid.org/0000-0002-9725-7747"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Cao","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9725-7747","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084710341","display_name":"Xiaoping Chen","orcid":"https://orcid.org/0000-0001-8992-9286"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoping Chen","raw_affiliation_strings":["School of Computer Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-8992-9286","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100362573","display_name":"Shiqi Zhang","orcid":"https://orcid.org/0000-0003-4110-8213"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shiqi Zhang","raw_affiliation_strings":["Department of Computer Science, State University of New York at Binghamton, Binghamton, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-4110-8213","affiliations":[{"raw_affiliation_string":"Department of Computer Science, State University of New York at Binghamton, Binghamton, NY, USA","institution_ids":["https://openalex.org/I123946342"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.273,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60100564,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"15","issue":"2","first_page":"395","last_page":"408"},"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":0.9991999864578247,"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":0.9968000054359436,"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/dialog-box","display_name":"Dialog box","score":0.972414493560791},{"id":"https://openalex.org/keywords/hindsight-bias","display_name":"Hindsight bias","score":0.943760871887207},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8297494649887085},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.757360577583313},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5544108748435974},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5402022004127502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5393611788749695},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4685657322406769},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.45141270756721497},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3805727958679199},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2993399500846863},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.11833733320236206},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.08427941799163818},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07308527827262878}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.972414493560791},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.943760871887207},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8297494649887085},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.757360577583313},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5544108748435974},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5402022004127502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5393611788749695},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4685657322406769},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.45141270756721497},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3805727958679199},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2993399500846863},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.11833733320236206},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.08427941799163818},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07308527827262878},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2021.3061121","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2021.3061121","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W47495561","https://openalex.org/W52170320","https://openalex.org/W86954431","https://openalex.org/W779494576","https://openalex.org/W1595483645","https://openalex.org/W1658008008","https://openalex.org/W1777239053","https://openalex.org/W1864247448","https://openalex.org/W1974721568","https://openalex.org/W1975244201","https://openalex.org/W1990671169","https://openalex.org/W2022163520","https://openalex.org/W2040123554","https://openalex.org/W2047335008","https://openalex.org/W2062175565","https://openalex.org/W2062244797","https://openalex.org/W2097381042","https://openalex.org/W2101524054","https://openalex.org/W2117989772","https://openalex.org/W2120045257","https://openalex.org/W2145339207","https://openalex.org/W2151253492","https://openalex.org/W2201581102","https://openalex.org/W2294065713","https://openalex.org/W2295072214","https://openalex.org/W2401657790","https://openalex.org/W2412715517","https://openalex.org/W2417401578","https://openalex.org/W2571927164","https://openalex.org/W2586680856","https://openalex.org/W2594726847","https://openalex.org/W2739936944","https://openalex.org/W2764174595","https://openalex.org/W2795520063","https://openalex.org/W2798494119","https://openalex.org/W2803790180","https://openalex.org/W2889186204","https://openalex.org/W2936674804","https://openalex.org/W2949252816","https://openalex.org/W2951805158","https://openalex.org/W2958341373","https://openalex.org/W2959918500","https://openalex.org/W2962776342","https://openalex.org/W2963043030","https://openalex.org/W2963064439","https://openalex.org/W2963068985","https://openalex.org/W2963140401","https://openalex.org/W2963252944","https://openalex.org/W2963433587","https://openalex.org/W2963523627","https://openalex.org/W2963800628","https://openalex.org/W2964044380","https://openalex.org/W2970272688","https://openalex.org/W2992753615","https://openalex.org/W2999091228","https://openalex.org/W3020018306","https://openalex.org/W3023592562","https://openalex.org/W3027990637","https://openalex.org/W3104546989","https://openalex.org/W4214717370","https://openalex.org/W4254718068","https://openalex.org/W4287867830","https://openalex.org/W4298857966","https://openalex.org/W4300554125","https://openalex.org/W4300799055","https://openalex.org/W4312609624","https://openalex.org/W6602127793","https://openalex.org/W6638088447","https://openalex.org/W6674600207","https://openalex.org/W6734696739","https://openalex.org/W6740801417","https://openalex.org/W6765527290","https://openalex.org/W6767151588"],"related_works":["https://openalex.org/W2500779211","https://openalex.org/W48079147","https://openalex.org/W326836678","https://openalex.org/W1963944933","https://openalex.org/W2563921006","https://openalex.org/W3012552522","https://openalex.org/W1600043506","https://openalex.org/W3133451788","https://openalex.org/W2755402024","https://openalex.org/W2963043030"],"abstract_inverted_index":{"Goal-oriented":[0],"dialog":[1,17,27,37,51,87,104,119,124,139,157,182,189],"systems":[2],"aim":[3],"to":[4,55,82,114,121,141,159],"efficiently":[5],"and":[6,64,136,165],"accurately":[7],"exchange":[8],"information":[9],"with":[10,61,127],"people":[11],"using":[12],"natural":[13],"language.":[14],"A":[15],"goal-oriented":[16],"policy":[18,52,88,105,190],"is":[19,47,92],"used":[20,34],"for":[21,25,35,176],"suggesting":[22],"language":[23],"actions":[24],"such":[26],"systems.":[28],"Reinforcement":[29],"learning":[30,125,191],"(RL)":[31],"has":[32],"been":[33],"computing":[36],"policies":[38],"from":[39,71,143,162],"the":[40,56,65,84,96,101,123,138,156,169,177],"experience":[41,70,167],"of":[42,59,86,99,103,117,187],"language-based":[43],"interaction.":[44],"Learning":[45],"efficiency":[46,85,102],"particularly":[48],"important":[49],"in":[50],"learning,":[53],"due":[54],"considerable":[57],"cost":[58],"interacting":[60],"human":[62],"users,":[63],"potentially":[66],"very":[67],"poor":[68],"user":[69,134],"low-quality":[72],"conversations.":[73],"In":[74],"this":[75],"article,":[76],"we":[77,108,132,148],"develop":[78],"deep":[79],"RL":[80],"algorithms":[81],"improve":[83],"learning.":[89,106],"Our":[90],"contribution":[91,174],"threefold,":[93],"aiming":[94],"at":[95,168],"central":[97],"goal":[98],"improving":[100],"First,":[107],"present":[109],"a":[110,151,185],"novel":[111],"\u201chindsight\u201d":[112],"approach":[113],"make":[115],"use":[116],"unsuccessful":[118],"instances":[120],"provide":[122],"agent":[126,140,158,183],"extra":[128],"positive":[129],"feedback.":[130],"Second,":[131],"introduce":[133],"modeling,":[135],"enable":[137],"learn":[142,161],"simulated":[144,163],"interaction":[145],"experience.":[146],"Third,":[147],"have":[149],"developed":[150],"metalearning":[152],"algorithm":[153],"that":[154],"enables":[155,180],"adaptively":[160],"users":[164],"hindsight":[166],"same":[170],"time.":[171],"The":[172],"threefold":[173],"altogether,":[175],"first":[178],"time,":[179],"our":[181,196],"outperforming":[184],"number":[186],"state-of-the-art":[188],"methods,":[192],"as":[193],"demonstrated":[194],"via":[195],"experimental":[197],"results.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}