{"id":"https://openalex.org/W2951805158","doi":"https://doi.org/10.1609/aaai.v33i01.33012596","title":"Goal-Oriented Dialogue Policy Learning from Failures","display_name":"Goal-Oriented Dialogue Policy Learning from Failures","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2951805158","doi":"https://doi.org/10.1609/aaai.v33i01.33012596","mag":"2951805158"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33012596","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33012596","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4107/3985","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4107/3985","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/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":"Keting Lu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","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":["State University of New York, Binghamton"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York, Binghamton","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"last","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":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7686,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97581672,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"33","issue":"01","first_page":"2596","last_page":"2603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10579","display_name":"Cognitive Radio Networks and Spectrum Sensing","score":0.9574000239372253,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10579","display_name":"Cognitive Radio Networks and Spectrum Sensing","score":0.9574000239372253,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10603","display_name":"Smart Grid Energy Management","score":0.9240999817848206,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9065999984741211,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/hindsight-bias","display_name":"Hindsight bias","score":0.9266761541366577},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8034069538116455},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7627676725387573},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.7452624440193176},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5780660510063171},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4191143214702606},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3995700180530548},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11933019757270813},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.09915176033973694}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.9266761541366577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8034069538116455},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7627676725387573},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.7452624440193176},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5780660510063171},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4191143214702606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3995700180530548},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11933019757270813},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.09915176033973694}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v33i01.33012596","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33012596","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4107/3985","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/4107","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/4107","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33012596","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33012596","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/4107/3985","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4000000059604645,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7566646584","display_name":null,"funder_award_id":"U1613216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320325599","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2951805158.pdf","grobid_xml":"https://content.openalex.org/works/W2951805158.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W47495561","https://openalex.org/W1595483645","https://openalex.org/W1658008008","https://openalex.org/W1777239053","https://openalex.org/W1786470251","https://openalex.org/W1864247448","https://openalex.org/W1975244201","https://openalex.org/W1990671169","https://openalex.org/W2040123554","https://openalex.org/W2047335008","https://openalex.org/W2062175565","https://openalex.org/W2120045257","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2294065713","https://openalex.org/W2412715517","https://openalex.org/W2417401578","https://openalex.org/W2571927164","https://openalex.org/W2586680856","https://openalex.org/W2728821832","https://openalex.org/W2739936944","https://openalex.org/W2764174595","https://openalex.org/W2949252816","https://openalex.org/W2963064439","https://openalex.org/W2963095800","https://openalex.org/W2963140401","https://openalex.org/W2964044380","https://openalex.org/W3104546989","https://openalex.org/W4214717370","https://openalex.org/W4300554125","https://openalex.org/W4300799055","https://openalex.org/W4312609624","https://openalex.org/W6602866055","https://openalex.org/W6677827304","https://openalex.org/W6677916085","https://openalex.org/W6687681856"],"related_works":["https://openalex.org/W3012552522","https://openalex.org/W4365788567","https://openalex.org/W3023592562","https://openalex.org/W4285382348","https://openalex.org/W3034773667","https://openalex.org/W2890406131","https://openalex.org/W4383758662","https://openalex.org/W4362475168","https://openalex.org/W4206195464","https://openalex.org/W4289666755"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,7,11,39,46,57,113],"methods":[2,71,99,106],"have":[3],"been":[4],"used":[5],"for":[6,80],"dialogue":[8,14,56,86],"policies.":[9],"However,":[10],"an":[12],"effective":[13],"policy":[15,87],"frequently":[16],"requires":[17],"prohibitively":[18],"many":[19],"conversations.":[20],"This":[21],"is":[22,53],"partly":[23],"because":[24],"of":[25],"the":[26,32,50,60,81],"sparse":[27],"rewards":[28],"in":[29,37,112],"dialogues,":[30],"and":[31,77],"very":[33],"few":[34],"successful":[35],"dialogues":[36],"early":[38],"phase.":[40],"Hindsight":[41],"experience":[42,104],"replay":[43,105],"(HER)":[44],"enables":[45],"from":[47],"failures,":[48],"but":[49],"vanilla":[51],"HER":[52,70,98],"inapplicable":[54],"to":[55,59,109],"due":[58],"implicit":[61],"goals.":[62],"In":[63],"this":[64],"work,":[65],"we":[66],"develop":[67],"two":[68],"complex":[69],"providing":[72],"different":[73],"tradeoffs":[74],"between":[75],"complexity":[76],"performance,":[78],"and,":[79],"first":[82],"time,":[83],"enabled":[84],"HER-based":[85],"learning.":[88],"Experiments":[89],"using":[90],"a":[91],"realistic":[92],"user":[93],"simulator":[94],"show":[95],"that":[96],"our":[97],"perform":[100],"better":[101],"than":[102],"existing":[103],"(as":[107],"applied":[108],"deep":[110],"Q-networks)":[111],"rate.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}