{"id":"https://openalex.org/W2732273801","doi":"https://doi.org/10.21437/interspeech.2017-1060","title":"Deep Reinforcement Learning of Dialogue Policies with Less Weight Updates","display_name":"Deep Reinforcement Learning of Dialogue Policies with Less Weight Updates","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2732273801","doi":"https://doi.org/10.21437/interspeech.2017-1060","mag":"2732273801"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-1060","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Deep_reinforcement_learning_of_dialogue_policies_with_less_weight_updates/25172426","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036357777","display_name":"Heriberto Cuay\u00e1huitl","orcid":"https://orcid.org/0000-0002-1937-9837"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Heriberto Cuay\u00e1huitl","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036671957","display_name":"Seunghak Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seunghak Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036357777"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0785,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90131817,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2511","last_page":"2515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9993000030517578,"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/T12031","display_name":"Speech and dialogue systems","score":0.9993000030517578,"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":0.9979000091552734,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8467836976051331},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8276089429855347},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.6931795477867126},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.6636114716529846},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.632015585899353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6129883527755737},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5635454654693604},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5625841617584229},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5000507831573486},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4451677203178406},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4205877482891083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467836976051331},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8276089429855347},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.6931795477867126},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.6636114716529846},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.632015585899353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6129883527755737},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5635454654693604},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5625841617584229},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5000507831573486},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4451677203178406},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4205877482891083},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2017-1060","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-1060","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.lincoln.ac.uk:27676","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196275","display_name":"Lincoln Repository (University of Lincoln)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I51532219","host_organization_name":"University of Lincoln","host_organization_lineage":["https://openalex.org/I51532219"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop contribution"},{"id":"pmh:oai:figshare.com:article/25172426","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Deep_reinforcement_learning_of_dialogue_policies_with_less_weight_updates/25172426","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/25172426","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Deep_reinforcement_learning_of_dialogue_policies_with_less_weight_updates/25172426","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1591706642","https://openalex.org/W1658008008","https://openalex.org/W1757796397","https://openalex.org/W1968962398","https://openalex.org/W1982262386","https://openalex.org/W2012918311","https://openalex.org/W2073384958","https://openalex.org/W2138394088","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2147169507","https://openalex.org/W2294065713","https://openalex.org/W2335959470","https://openalex.org/W2412899141","https://openalex.org/W2418993857","https://openalex.org/W2425426841","https://openalex.org/W2553109721","https://openalex.org/W2558661633","https://openalex.org/W2559038528","https://openalex.org/W2603550564","https://openalex.org/W2886444114","https://openalex.org/W2963167310","https://openalex.org/W2963477884","https://openalex.org/W2963993502","https://openalex.org/W2963993719","https://openalex.org/W2964043796"],"related_works":["https://openalex.org/W618248309","https://openalex.org/W2377336366","https://openalex.org/W1568097102","https://openalex.org/W4390419160","https://openalex.org/W1601203902","https://openalex.org/W2075798043","https://openalex.org/W2102464536","https://openalex.org/W4225671779","https://openalex.org/W2361332776","https://openalex.org/W3034267371"],"abstract_inverted_index":{"<p>Deep":[0],"reinforcement":[1],"learning":[2,69,112],"dialogue":[3,43,160],"systems":[4],"are":[5,153],"attractive":[6],"because":[7],"they":[8],"can":[9],"jointly":[10],"learn":[11],"their":[12],"feature":[13,19],"representations":[14],"and":[15,91,105,131],"policies":[16,140],"without":[17,147],"manual":[18],"engineering.":[20],"But":[21],"its":[22],"application":[23],"is":[24,114],"challenging":[25],"due":[26],"to":[27],"slow":[28],"learning.":[29],"We":[30],"propose":[31],"a":[32,145],"two-stage":[33],"method":[34,138],"for":[35,155],"accelerating":[36],"the":[37,46,50,57,80,83,93,136,148],"induction":[38],"of":[39,52,82,89,95],"single":[40],"or":[41],"multi-domain":[42],"policies.":[44],"While":[45],"first":[47],"stage":[48,59],"reduces":[49],"amount":[51,94],"weight":[53,118],"updates":[54,79,96,102,108,119],"over":[55],"time,":[56],"second":[58],"uses":[60],"very":[61],"limited":[62],"minibatches":[63],"(of":[64],"as":[65,67,97],"much":[66],"two":[68],"experiences)":[70],"sampled":[71],"from":[72],"experience":[73],"replay":[74],"memories.":[75],"The":[76,111],"former":[77],"frequently":[78],"weights":[81],"neural":[84],"nets":[85],"at":[86],"early":[87],"stages":[88],"training,":[90],"decreases":[92],"training":[98,156],"progresses":[99],"by":[100,106],"performing":[101],"during":[103,109],"exploration":[104],"skipping":[107],"exploitation.":[110],"process":[113],"thus":[115],"acceleratedthrough":[116],"less":[117],"in":[120,126],"both":[121],"stages.":[122],"An":[123],"empirical":[124],"evaluation":[125],"three":[127],"domains":[128],"(restaurants,":[129],"hotels":[130],"tv":[132],"guide)":[133],"confirms":[134],"that":[135],"proposed":[137,149],"trains":[139],"5":[141],"times":[142],"faster":[143],"than":[144],"baseline":[146],"method.":[150],"Our":[151],"findings":[152],"useful":[154],"larger-scale":[157],"neural-based":[158],"spoken":[159],"systems.</p>":[161]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}