{"id":"https://openalex.org/W2892176966","doi":"https://doi.org/10.1109/icassp.2018.8462272","title":"Policy Adaptation for Deep Reinforcement Learning-Based Dialogue Management","display_name":"Policy Adaptation for Deep Reinforcement Learning-Based Dialogue Management","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2892176966","doi":"https://doi.org/10.1109/icassp.2018.8462272","mag":"2892176966"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100605099","display_name":"Chen L\u00fc","orcid":"https://orcid.org/0000-0003-1927-2391"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, Center Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Center Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101987170","display_name":"Cheng Chang","orcid":"https://orcid.org/0000-0001-6589-4437"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Chang","raw_affiliation_strings":["Department of Computer Science and Engineering, Center Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Center Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100456850","display_name":"Zhi Chen","orcid":"https://orcid.org/0000-0003-4180-8455"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, Center Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Center Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101403295","display_name":"Bowen Tan","orcid":"https://orcid.org/0000-0003-3036-2881"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Tan","raw_affiliation_strings":["Department of Computer Science and Engineering, Center Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Center Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"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":["Engineering Department, University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Department, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kai Yu","raw_affiliation_strings":["Department of Computer Science and Engineering, Center Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Center Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6074","last_page":"6078"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":1.0,"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":1.0,"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":0.9990000128746033,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9947999715805054,"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":0.8819761276245117},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7742937803268433},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.6815626621246338},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6380244493484497},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.6297141313552856},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6081752777099609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.559781014919281},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5426623225212097},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.4864639937877655},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.48093241453170776},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.47988927364349365},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.43562671542167664},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3524209260940552},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0981099009513855}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8819761276245117},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7742937803268433},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6815626621246338},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6380244493484497},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.6297141313552856},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6081752777099609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.559781014919281},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5426623225212097},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.4864639937877655},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.48093241453170776},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.47988927364349365},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.43562671542167664},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3524209260940552},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0981099009513855},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2018.8462272","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462272","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:1032729","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/1032729/","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":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1948566616","https://openalex.org/W1975244201","https://openalex.org/W1993567041","https://openalex.org/W2044704181","https://openalex.org/W2062175565","https://openalex.org/W2099618002","https://openalex.org/W2145339207","https://openalex.org/W2175723363","https://openalex.org/W2251058040","https://openalex.org/W2252011326","https://openalex.org/W2395575420","https://openalex.org/W2412899141","https://openalex.org/W2519349389","https://openalex.org/W2594726847","https://openalex.org/W2759104452","https://openalex.org/W2759567155","https://openalex.org/W2772001136","https://openalex.org/W2949252816","https://openalex.org/W2962776342","https://openalex.org/W2963993502","https://openalex.org/W2963993719","https://openalex.org/W2964044380","https://openalex.org/W2964338167","https://openalex.org/W6640958697","https://openalex.org/W6648827013","https://openalex.org/W6661689888","https://openalex.org/W6691368330","https://openalex.org/W6713411898","https://openalex.org/W6715092320","https://openalex.org/W6715753392","https://openalex.org/W6734696739","https://openalex.org/W6740105557","https://openalex.org/W6744697566","https://openalex.org/W6744705064","https://openalex.org/W6746371061"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W3095487414","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W2901026139"],"abstract_inverted_index":{"Policy":[0],"optimization":[1,20],"is":[2,50,58,97],"the":[3,28,53,63,74,130,136,145,159],"core":[4],"part":[5],"of":[6,105],"statistical":[7],"dialogue":[8,18,64,86,94],"management.":[9],"Deep":[10],"reinforcement":[11],"learning":[12,161],"has":[13],"been":[14],"successfully":[15],"used":[16,44],"for":[17,21,55,77,124],"policy":[19,54,87,95,128,160,164],"a":[22,33,46,91,111],"static":[23],"pre-defined":[24],"domain.":[25,149],"However,":[26],"when":[27],"domain":[29,57],"changes":[30],"dynamically,":[31],"e.g.":[32],"new":[34],"previously":[35],"unseen":[36],"concept":[37],"(or":[38],"slot)":[39],"which":[40],"can":[41,140,155],"be":[42,82,141],"then":[43],"as":[45],"database":[47],"search":[48],"constraint":[49],"added,":[51],"or":[52],"one":[56],"transferred":[59,143],"to":[60,81,99,121,144],"another":[61],"domain,":[62],"state":[65],"space":[66],"and":[67,110,135,162],"action":[68],"sets":[69],"both":[70],"will":[71],"change.":[72],"Therefore,":[73],"model":[75],"structures":[76],"different":[78],"domains":[79],"have":[80,116],"different.":[83],"This":[84],"makes":[85],"adaptation/transfer":[88],"challenging.":[89],"Here":[90],"multi":[92],"-agent":[93],"(MADP)":[96],"proposed":[98],"tackle":[100],"these":[101],"problems.":[102],"MADP":[103,154],"consists":[104],"some":[106],"slot-dependent":[107],"agents":[108,146],"(S-Agents)":[109],"slot-independent":[112],"agent":[113],"(G-Agent).":[114],"S-Agents":[115,134],"shared":[117,131],"parameters":[118,123,132,137],"in":[119,133,138,147],"addition":[120],"private":[122],"each":[125],"one.":[126],"During":[127],"transfer,":[129],"G-Agent":[139],"directly":[142],"extended/new":[148],"Simulation":[150],"experiments":[151],"showed":[152],"that":[153],"significantly":[156],"speed":[157],"up":[158],"facilitate":[163],"adaptation.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}