{"id":"https://openalex.org/W2964044380","doi":"https://doi.org/10.18653/v1/w17-5518","title":"Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management","display_name":"Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2964044380","doi":"https://doi.org/10.18653/v1/w17-5518","mag":"2964044380"},"language":"en","primary_location":{"id":"doi:10.18653/v1/w17-5518","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-5518","pdf_url":"https://www.aclweb.org/anthology/W17-5518.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 18th Annual SIGdial Meeting on Discourse and Dialogue","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/W17-5518.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040922365","display_name":"Pei-Hao Su","orcid":"https://orcid.org/0000-0002-6606-6016"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pei-Hao Su","raw_affiliation_strings":["Department of Engineering, University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088210639","display_name":"Pawe\u0142 Budzianowski","orcid":"https://orcid.org/0000-0003-0013-7931"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pawe\u0142 Budzianowski","raw_affiliation_strings":["Department of Engineering, University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058838995","display_name":"Stefan Ultes","orcid":"https://orcid.org/0000-0003-2667-3126"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Stefan Ultes","raw_affiliation_strings":["Department of Engineering, University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051889115","display_name":"Milica Ga\u0161i\u0107","orcid":"https://orcid.org/0000-0003-0318-9147"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Milica Gasic","raw_affiliation_strings":["Department of Engineering, University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109097977","display_name":"Steve Young","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Steve Young","raw_affiliation_strings":["Department of Engineering, University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":9.6897,"has_fulltext":true,"cited_by_count":119,"citation_normalized_percentile":{"value":0.98568797,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"147","last_page":"157"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9944000244140625,"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":0.9765999913215637,"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":0.9353131055831909},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8165549635887146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7101795673370361},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6080396175384521},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5502665638923645},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49589213728904724},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47332486510276794},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4668567478656769},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.42573463916778564},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4103505611419678},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07765647768974304}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9353131055831909},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8165549635887146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7101795673370361},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6080396175384521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5502665638923645},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49589213728904724},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47332486510276794},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4668567478656769},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.42573463916778564},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4103505611419678},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07765647768974304},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/w17-5518","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-5518","pdf_url":"https://www.aclweb.org/anthology/W17-5518.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 18th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/w17-5518","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/w17-5518","pdf_url":"https://www.aclweb.org/anthology/W17-5518.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 18th Annual SIGdial Meeting on Discourse and Dialogue","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321848","display_name":"Cambridge Trust","ror":"https://ror.org/05sprqy15"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964044380.pdf","grobid_xml":"https://content.openalex.org/works/W2964044380.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W200223693","https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1590243462","https://openalex.org/W1591706642","https://openalex.org/W1600046456","https://openalex.org/W1771410628","https://openalex.org/W1932421248","https://openalex.org/W1948566616","https://openalex.org/W1969152782","https://openalex.org/W1970789124","https://openalex.org/W1975244201","https://openalex.org/W1980340273","https://openalex.org/W1980516134","https://openalex.org/W1999184850","https://openalex.org/W2007221309","https://openalex.org/W2015936967","https://openalex.org/W2021151961","https://openalex.org/W2022398498","https://openalex.org/W2035934535","https://openalex.org/W2047335008","https://openalex.org/W2054716580","https://openalex.org/W2092795326","https://openalex.org/W2101445408","https://openalex.org/W2117398305","https://openalex.org/W2119717200","https://openalex.org/W2127107099","https://openalex.org/W2133733518","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2154740693","https://openalex.org/W2155027007","https://openalex.org/W2168490009","https://openalex.org/W2214131199","https://openalex.org/W2250297846","https://openalex.org/W2251221343","https://openalex.org/W2252011326","https://openalex.org/W2257979135","https://openalex.org/W2289601637","https://openalex.org/W2296712013","https://openalex.org/W2312609093","https://openalex.org/W2417401578","https://openalex.org/W2438667436","https://openalex.org/W2473965551","https://openalex.org/W2474694648","https://openalex.org/W2560678344","https://openalex.org/W2577837170","https://openalex.org/W2591807639","https://openalex.org/W2594726847","https://openalex.org/W2607198029","https://openalex.org/W2746553466","https://openalex.org/W2962847367","https://openalex.org/W2963064439","https://openalex.org/W2963095800","https://openalex.org/W2963167310","https://openalex.org/W2963252944","https://openalex.org/W2963295373","https://openalex.org/W2963797754","https://openalex.org/W2963963856","https://openalex.org/W2963993502","https://openalex.org/W2964080167","https://openalex.org/W2964101860","https://openalex.org/W2964121744","https://openalex.org/W2964210218","https://openalex.org/W3086499488","https://openalex.org/W4251193772","https://openalex.org/W4254755460","https://openalex.org/W4285719527","https://openalex.org/W4295249402"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,139],"learning":[2,31,48,81,111,151],"(RL)":[3],"methods":[4],"have":[5],"significant":[6],"potential":[7],"for":[8,29],"dialogue":[9,154],"policy":[10,100],"optimisation.":[11],"However,":[12],"they":[13],"suffer":[14],"from":[15],"a":[16,125,147,161],"poor":[17],"performance":[18],"in":[19,99,160],"the":[20,47,74,80,91,95,105,121,134],"early":[21],"stages":[22],"of":[23,127],"learning.":[24,140],"This":[25],"is":[26,130],"especially":[27],"problematic":[28],"on-line":[30,138],"with":[32,58,66,112],"real":[33],"users.":[34],"Two":[35],"approaches":[36],"are":[37,70],"introduced":[38],"to":[39,44,78,102,115,119,132,137,150],"tackle":[40],"this":[41],"problem.":[42],"Firstly,":[43],"speed":[45,103],"up":[46,104],"process,":[49],"two":[50,143],"sampleefficient":[51],"neural":[52],"networks":[53],"algorithms:":[54],"trust":[55,75],"region":[56,76],"actor-critic":[57],"experience":[59,67,113],"replay":[60,68,114],"(TRACER)":[61],"and":[62,84,156],"episodic":[63],"natural":[64,92],"actorcritic":[65],"(eNACER)":[69],"presented.":[71],"For":[72,89],"TRACER,":[73],"helps":[77],"control":[79],"step":[82],"size":[83],"avoid":[85],"catastrophic":[86],"model":[87],"changes.":[88],"eNACER,":[90],"gradient":[93],"identifies":[94],"steepest":[96],"ascent":[97],"direction":[98],"space":[101],"convergence.":[106],"Both":[107],"models":[108,135],"employ":[109],"off-policy":[110],"improve":[116],"sampleefficiency.":[117],"Secondly,":[118],"mitigate":[120],"cold":[122],"start":[123],"issue,":[124],"corpus":[126],"demonstration":[128],"data":[129],"utilised":[131],"pre-train":[133],"prior":[136],"Combining":[141],"these":[142],"approaches,":[144],"we":[145],"demonstrate":[146,157],"practical":[148],"approach":[149],"deep":[152],"RLbased":[153],"policies":[155],"their":[158],"effectiveness":[159],"task-oriented":[162],"information":[163],"seeking":[164],"domain.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":17},{"year":2021,"cited_by_count":22},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":20},{"year":2017,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}