{"id":"https://openalex.org/W4313703382","doi":"https://doi.org/10.1007/s11633-022-1347-y","title":"A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-oriented Dialogue Policy Learning","display_name":"A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-oriented Dialogue Policy Learning","publication_year":2023,"publication_date":"2023-01-07","ids":{"openalex":"https://openalex.org/W4313703382","doi":"https://doi.org/10.1007/s11633-022-1347-y"},"language":"en","primary_location":{"id":"doi:10.1007/s11633-022-1347-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-022-1347-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-022-1347-y.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11633-022-1347-y.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068169387","display_name":"Wai-Chung Kwan","orcid":"https://orcid.org/0000-0002-2942-4208"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Wai-Chung Kwan","raw_affiliation_strings":["The Systems Engineering and Engineering Management Department, The Chinese University of Hong Kong, Hong Kong, 999077, China"],"raw_orcid":"https://orcid.org/0000-0002-2942-4208","affiliations":[{"raw_affiliation_string":"The Systems Engineering and Engineering Management Department, The Chinese University of Hong Kong, Hong Kong, 999077, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077637321","display_name":"Hongru Wang","orcid":"https://orcid.org/0000-0001-5027-0138"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hong-Ru Wang","raw_affiliation_strings":["The Systems Engineering and Engineering Management Department, The Chinese University of Hong Kong, Hong Kong, 999077, China"],"raw_orcid":"https://orcid.org/0000-0001-5027-0138","affiliations":[{"raw_affiliation_string":"The Systems Engineering and Engineering Management Department, The Chinese University of Hong Kong, Hong Kong, 999077, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009639089","display_name":"Huimin Wang","orcid":"https://orcid.org/0000-0002-6147-8310"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hui-Min Wang","raw_affiliation_strings":["The Systems Engineering and Engineering Management Department, The Chinese University of Hong Kong, Hong Kong, 999077, China"],"raw_orcid":"https://orcid.org/0000-0002-6147-8310","affiliations":[{"raw_affiliation_string":"The Systems Engineering and Engineering Management Department, The Chinese University of Hong Kong, Hong Kong, 999077, China","institution_ids":["https://openalex.org/I177725633"]}]},{"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":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kam-Fai Wong","raw_affiliation_strings":["The Systems Engineering and Engineering Management Department, The Chinese University of Hong Kong, Hong Kong, 999077, China"],"raw_orcid":"https://orcid.org/0000-0002-9427-5659","affiliations":[{"raw_affiliation_string":"The Systems Engineering and Engineering Management Department, The Chinese University of Hong Kong, Hong Kong, 999077, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5068169387"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":5.6958,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.96780421,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"20","issue":"3","first_page":"318","last_page":"334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9998999834060669,"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":0.9998999834060669,"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/T12128","display_name":"AI in Service Interactions","score":0.9958000183105469,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8586829304695129},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6924768686294556},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.676699161529541},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.6452333927154541},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6132175326347351},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.514411985874176},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.47983428835868835},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4645279347896576},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4258323311805725},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39472922682762146},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35304585099220276},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.17069613933563232},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09163066744804382},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0634031891822815}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8586829304695129},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6924768686294556},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.676699161529541},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.6452333927154541},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6132175326347351},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.514411985874176},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47983428835868835},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4645279347896576},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4258323311805725},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39472922682762146},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35304585099220276},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.17069613933563232},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09163066744804382},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0634031891822815},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11633-022-1347-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-022-1347-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-022-1347-y.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11633-022-1347-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-022-1347-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-022-1347-y.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4000000059604645}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326427","display_name":"Innovation and Technology Fund","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4313703382.pdf"},"referenced_works_count":102,"referenced_works":["https://openalex.org/W143053999","https://openalex.org/W1681299129","https://openalex.org/W1777239053","https://openalex.org/W1975244201","https://openalex.org/W1999874108","https://openalex.org/W2005814556","https://openalex.org/W2021151961","https://openalex.org/W2022398498","https://openalex.org/W2031571562","https://openalex.org/W2062175565","https://openalex.org/W2062244797","https://openalex.org/W2064675550","https://openalex.org/W2089327077","https://openalex.org/W2106547558","https://openalex.org/W2108366050","https://openalex.org/W2109038907","https://openalex.org/W2109910161","https://openalex.org/W2120045257","https://openalex.org/W2121517924","https://openalex.org/W2125612430","https://openalex.org/W2132997613","https://openalex.org/W2133068870","https://openalex.org/W2151814822","https://openalex.org/W2152342063","https://openalex.org/W2162046402","https://openalex.org/W2165698076","https://openalex.org/W2171079152","https://openalex.org/W2171486046","https://openalex.org/W2187436616","https://openalex.org/W2214131199","https://openalex.org/W2257979135","https://openalex.org/W2396863940","https://openalex.org/W2592215206","https://openalex.org/W2603550564","https://openalex.org/W2739936944","https://openalex.org/W2761412636","https://openalex.org/W2765111838","https://openalex.org/W2798389811","https://openalex.org/W2798494119","https://openalex.org/W2806936550","https://openalex.org/W2810840719","https://openalex.org/W2889165300","https://openalex.org/W2889186204","https://openalex.org/W2892176966","https://openalex.org/W2900082869","https://openalex.org/W2915295540","https://openalex.org/W2921511174","https://openalex.org/W2949476504","https://openalex.org/W2951805158","https://openalex.org/W2953071719","https://openalex.org/W2962776342","https://openalex.org/W2962852262","https://openalex.org/W2962886331","https://openalex.org/W2963043030","https://openalex.org/W2963064439","https://openalex.org/W2963140401","https://openalex.org/W2963246392","https://openalex.org/W2963252944","https://openalex.org/W2963295373","https://openalex.org/W2963306198","https://openalex.org/W2963433587","https://openalex.org/W2963963856","https://openalex.org/W2963993502","https://openalex.org/W2964018203","https://openalex.org/W2964044380","https://openalex.org/W2964080167","https://openalex.org/W2964101860","https://openalex.org/W2964180249","https://openalex.org/W2964227312","https://openalex.org/W2970828515","https://openalex.org/W2970866659","https://openalex.org/W2979372603","https://openalex.org/W2979400990","https://openalex.org/W2997108628","https://openalex.org/W3019549080","https://openalex.org/W3020018306","https://openalex.org/W3022352842","https://openalex.org/W3023592562","https://openalex.org/W3034330559","https://openalex.org/W3034441005","https://openalex.org/W3034656193","https://openalex.org/W3034782127","https://openalex.org/W3034930293","https://openalex.org/W3035337525","https://openalex.org/W3035597485","https://openalex.org/W3088273075","https://openalex.org/W3101282510","https://openalex.org/W3104546989","https://openalex.org/W3105184920","https://openalex.org/W3176706409","https://openalex.org/W3208837891","https://openalex.org/W3214586773","https://openalex.org/W4214717370","https://openalex.org/W4290742115","https://openalex.org/W4312609624","https://openalex.org/W4389009381","https://openalex.org/W6635590879","https://openalex.org/W6637967152","https://openalex.org/W6716955619","https://openalex.org/W6731619401","https://openalex.org/W6734847233","https://openalex.org/W6779337559"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Abstract":[0],"Dialogue":[1],"policy":[2,83,102],"learning":[3,41,53],"(DPL)":[4],"is":[5,17,43,57],"a":[6,10,36,108],"key":[7],"component":[8],"in":[9,81,124,136],"task-oriented":[11],"dialogue":[12,25,29,38,49,82,101],"(TOD)":[13],"system.":[14],"Its":[15],"goal":[16],"to":[18,46,114],"decide":[19],"the":[20,24,28,52,55,60,63,66,76,85,93],"next":[21],"action":[22],"of":[23,75,87,111],"system,":[26],"given":[27],"state":[30],"at":[31],"each":[32],"turn":[33],"based":[34],"on":[35,133],"learned":[37],"policy.":[39,50],"Reinforcement":[40],"(RL)":[42],"widely":[44],"used":[45],"optimize":[47],"this":[48,69,128],"In":[51,68,104],"process,":[54],"user":[56],"regarded":[58],"as":[59,65],"environment":[61],"and":[62,79,95],"system":[64],"agent.":[67],"paper,":[70],"we":[71,91,106],"present":[72],"an":[73],"overview":[74],"recent":[77,118],"advances":[78],"challenges":[80],"from":[84],"perspective":[86],"RL.":[88,125],"More":[89],"specifically,":[90],"identify":[92],"problems":[94],"summarize":[96],"corresponding":[97],"solutions":[98],"for":[99],"RL-based":[100],"learning.":[103],"addition,":[105],"provide":[107],"comprehensive":[109],"survey":[110,129],"applying":[112],"RL":[113],"DPL":[115],"by":[116],"categorizing":[117],"methods":[119],"into":[120],"five":[121],"basic":[122],"elements":[123],"We":[126],"believe":[127],"can":[130],"shed":[131],"light":[132],"future":[134],"research":[135],"DPL.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}