{"id":"https://openalex.org/W2785612489","doi":"https://doi.org/10.1109/taslp.2018.2851664","title":"Sample Efficient Deep Reinforcement Learning for Dialogue Systems With Large Action Spaces","display_name":"Sample Efficient Deep Reinforcement Learning for Dialogue Systems With Large Action Spaces","publication_year":2018,"publication_date":"2018-07-03","ids":{"openalex":"https://openalex.org/W2785612489","doi":"https://doi.org/10.1109/taslp.2018.2851664","mag":"2785612489"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2018.2851664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2851664","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1802.03753","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011892682","display_name":"Gell\u00e9rt Weisz","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"]},{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":true,"raw_author_name":"Gellert Weisz","raw_affiliation_strings":["DeepMind Technologies, London, U.K","Department of Engineering, University of Cambridge, Cambridge, U.K","Department of Engineering, University of Cambridge, Cambridge, U. K"],"affiliations":[{"raw_affiliation_string":"DeepMind Technologies, London, U.K","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, U. K","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]},{"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"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Pawel Budzianowski","raw_affiliation_strings":["Department of Engineering, University of Cambridge, Cambridge, U.K","Department of Engineering, University of Cambridge, Cambridge, U. K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, U. K","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]},{"author_position":"middle","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"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]},{"id":"https://openalex.org/I86908984","display_name":"University of French Polynesia","ror":"https://ror.org/03ay59x86","country_code":"PF","type":"education","lineage":["https://openalex.org/I86908984"]}],"countries":["GB","PF","SS"],"is_corresponding":false,"raw_author_name":"Pei-Hao Su","raw_affiliation_strings":["Department of Engineering, University of Cambridge, Cambridge, U.K","PolyAI, London, U.K","Department of Engineering, University of Cambridge, Cambridge, U. K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"PolyAI, London, U.K","institution_ids":["https://openalex.org/I86908984"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, U. K","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]},{"author_position":"last","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"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Milica Gasic","raw_affiliation_strings":["Department of Engineering, University of Cambridge, Cambridge, U.K","Department of Engineering, University of Cambridge, Cambridge, U. K"],"affiliations":[{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, U.K","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, U. K","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5011892682"],"corresponding_institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210090411","https://openalex.org/I4210096386"],"apc_list":null,"apc_paid":null,"fwci":0.8462,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79618236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"26","issue":"11","first_page":"2083","last_page":"2097"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T12031","display_name":"Speech and dialogue systems","score":0.9976999759674072,"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":0.9965000152587891,"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":0.8507115840911865},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7694225311279297},{"id":"https://openalex.org/keywords/converse","display_name":"Converse","score":0.7437477111816406},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.6324993968009949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6264446973800659},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5636507868766785},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5585489869117737},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.49660950899124146},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.49190354347229004},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.4885023832321167},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4860144257545471},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4836636483669281},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46718648076057434},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43165159225463867},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4305840730667114},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4140036702156067},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17007949948310852},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10615378618240356},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0830329954624176}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8507115840911865},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7694225311279297},{"id":"https://openalex.org/C2776809875","wikidata":"https://www.wikidata.org/wiki/Q1375963","display_name":"Converse","level":2,"score":0.7437477111816406},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.6324993968009949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6264446973800659},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5636507868766785},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5585489869117737},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.49660950899124146},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49190354347229004},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.4885023832321167},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4860144257545471},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4836636483669281},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46718648076057434},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43165159225463867},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4305840730667114},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4140036702156067},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17007949948310852},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10615378618240356},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0830329954624176},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","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/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0}],"mesh":[],"locations_count":8,"locations":[{"id":"doi:10.1109/taslp.2018.2851664","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2018.2851664","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1802.03753","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.03753","pdf_url":"https://arxiv.org/pdf/1802.03753","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2785612489","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1802.03753","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:doi:10.17863/cam.31486","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:generic.eprints.org:1010530","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/1010530/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:www.repository.cam.ac.uk:1810/284115","is_oa":false,"landing_page_url":"https://www.repository.cam.ac.uk/handle/1810/284115","pdf_url":null,"source":{"id":"https://openalex.org/S4306401776","display_name":"Apollo (University of Cambridge)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I241749","host_organization_name":"University of Cambridge","host_organization_lineage":["https://openalex.org/I241749"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.1802.03753","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1802.03753","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17863/cam.31486","is_oa":true,"landing_page_url":"https://doi.org/10.17863/cam.31486","pdf_url":null,"source":{"id":"https://openalex.org/S7407050737","display_name":"Apollo","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1802.03753","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1802.03753","pdf_url":"https://arxiv.org/pdf/1802.03753","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W47495561","https://openalex.org/W1600046456","https://openalex.org/W1602011256","https://openalex.org/W1975244201","https://openalex.org/W1978616112","https://openalex.org/W2007221309","https://openalex.org/W2047335008","https://openalex.org/W2062175565","https://openalex.org/W2108806737","https://openalex.org/W2117555338","https://openalex.org/W2121863487","https://openalex.org/W2127107099","https://openalex.org/W2141559645","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2167117957","https://openalex.org/W2168359464","https://openalex.org/W2172501646","https://openalex.org/W2172968643","https://openalex.org/W2175723363","https://openalex.org/W2410985346","https://openalex.org/W2412715517","https://openalex.org/W2412899141","https://openalex.org/W2507592741","https://openalex.org/W2577837170","https://openalex.org/W2594726847","https://openalex.org/W2604688337","https://openalex.org/W2739936944","https://openalex.org/W2785612489","https://openalex.org/W2949608212","https://openalex.org/W2963043030","https://openalex.org/W2963068985","https://openalex.org/W2963797754","https://openalex.org/W2963993719","https://openalex.org/W2964044380","https://openalex.org/W2964121744","https://openalex.org/W2964309400","https://openalex.org/W4300554125","https://openalex.org/W6631190155","https://openalex.org/W6635798015","https://openalex.org/W6635849714","https://openalex.org/W6638018090","https://openalex.org/W6639024717","https://openalex.org/W6653435097","https://openalex.org/W6676271009","https://openalex.org/W6683001934","https://openalex.org/W6683204974","https://openalex.org/W6715092320","https://openalex.org/W6715102896","https://openalex.org/W6715475388","https://openalex.org/W6715753392","https://openalex.org/W6730111887","https://openalex.org/W6734696739","https://openalex.org/W6736009505","https://openalex.org/W6738601716","https://openalex.org/W6743980790","https://openalex.org/W6753541276","https://openalex.org/W6755316412"],"related_works":["https://openalex.org/W2950038834","https://openalex.org/W3200695557","https://openalex.org/W2999490157","https://openalex.org/W52170320","https://openalex.org/W2128786740","https://openalex.org/W2895434601","https://openalex.org/W2902567911","https://openalex.org/W3005607450","https://openalex.org/W2950197980","https://openalex.org/W3171051732","https://openalex.org/W276460289","https://openalex.org/W3163571701","https://openalex.org/W2890026535","https://openalex.org/W3036236109","https://openalex.org/W2890077990","https://openalex.org/W2899041500","https://openalex.org/W3084024636","https://openalex.org/W2782997251","https://openalex.org/W3159952121","https://openalex.org/W2158641818"],"abstract_inverted_index":{"In":[0,62],"spoken":[1,162],"dialogue":[2,13,54,142,163],"systems,":[3],"we":[4,65,135],"aim":[5],"to":[6,10,32,38,40,71,79,141,169,183],"deploy":[7],"artificial":[8],"intelligence":[9],"build":[11],"automated":[12],"agents":[14],"that":[15,111,147,175,217],"can":[16,176],"converse":[17],"with":[18,85,196],"humans.":[19],"A":[20],"part":[21],"of":[22,45,52,59,98,139,154,208,226],"this":[23,63,73,133,148],"effort":[24],"is":[25,77],"the":[26,43,49,53,57,60,94,106,137,151,155,185,223,227],"policy":[27,35,143],"optimization":[28],"task,":[29],"which":[30,204],"attempts":[31],"find":[33,216],"a":[34,46,126,170,199],"describing":[36],"how":[37],"respond":[39],"humans,":[41],"in":[42,105,115,132,157,187,198],"form":[44],"function":[47],"taking":[48],"current":[50,152,224],"state":[51,153,225],"and":[55,88,96,124],"returning":[56],"response":[58],"system.":[61],"paper,":[64,134],"investigate":[66],"deep":[67,158],"reinforcement":[68,83],"learning":[69,84,159,197],"approaches":[70,160],"solve":[72],"problem.":[74],"Particular":[75],"attention":[76],"given":[78],"actor-critic":[80],"methods,":[81],"off-policy":[82],"experience":[86],"replay,":[87],"various":[89],"methods":[90,103],"aimed":[91],"at":[92],"reducing":[93],"bias":[95],"variance":[97],"estimators.":[99],"When":[100],"combined,":[101],"these":[102],"result":[104],"previously":[107,213],"proposed":[108],"ACER":[109,140,218],"algorithm":[110,174,186],"gave":[112],"competitive":[113],"results":[114],"gaming":[116],"environments.":[117],"These":[118],"environments,":[119],"however,":[120],"are":[121],"fully":[122],"observable":[123],"have":[125],"relatively":[127],"small":[128],"action":[129,202],"set":[130],"so,":[131],"examine":[136],"application":[138],"optimization.":[144],"We":[145,193,215],"show":[146],"method":[149],"beats":[150],"art":[156],"for":[161],"systems.":[164],"This":[165],"not":[166],"only":[167],"leads":[168],"more":[171,188,210],"sample":[172],"efficient":[173],"train":[177],"faster,":[178],"but":[179],"also":[180],"allows":[181],"us":[182],"apply":[184],"difficult":[189],"environments":[190],"than":[191,212,222],"before.":[192],"thus":[194],"experiment":[195],"very":[200],"large":[201],"space,":[203],"has":[205],"two":[206],"orders":[207],"magnitude":[209],"actions":[211],"considered.":[214],"trains":[219],"significantly":[220],"faster":[221],"art.":[228]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}