{"id":"https://openalex.org/W3074656709","doi":"https://doi.org/10.1109/access.2020.3017780","title":"Policy Reuse for Dialog Management Using Action-Relation Probability","display_name":"Policy Reuse for Dialog Management Using Action-Relation Probability","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3074656709","doi":"https://doi.org/10.1109/access.2020.3017780","mag":"3074656709"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.3017780","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3017780","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09171319.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09171319.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041850371","display_name":"Tung T. Nguyen","orcid":"https://orcid.org/0000-0001-5166-4606"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tung T. Nguyen","raw_affiliation_strings":["Nara Institute of Science and Technology, Ikoma, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101880946","display_name":"Koichiro Yoshino","orcid":"https://orcid.org/0000-0001-6579-361X"},"institutions":[{"id":"https://openalex.org/I4210086780","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19","country_code":"JP","type":"government","lineage":["https://openalex.org/I4210086780"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koichiro Yoshino","raw_affiliation_strings":["Japan Science and Technology Agency, Kawaguchi, Japan","Nara Institute of Science and Technology, Ikoma, Japan"],"affiliations":[{"raw_affiliation_string":"Japan Science and Technology Agency, Kawaguchi, Japan","institution_ids":["https://openalex.org/I4210086780"]},{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Center for Advanced Intelligence Project AIP, Ikoma, Japan","Nara Institute of Science and Technology, Ikoma, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project AIP, Ikoma, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I4210126580","display_name":"RIKEN Center for Advanced Intelligence Project","ror":"https://ror.org/03ckxwf91","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210126580"]},{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Center for Advanced Intelligence Project AIP, Ikoma, Japan","Nara Institute of Science and Technology, Ikoma, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Advanced Intelligence Project AIP, Ikoma, Japan","institution_ids":["https://openalex.org/I4210126580"]},{"raw_affiliation_string":"Nara Institute of Science and Technology, Ikoma, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5041850371"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09621,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"159639","last_page":"159649"},"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":0.9993000030517578,"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/T12128","display_name":"AI in Service Interactions","score":0.9940999746322632,"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/dialog-box","display_name":"Dialog box","score":0.915908694267273},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8770671486854553},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8413625955581665},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7457406520843506},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7234867215156555},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.569308340549469},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5439320802688599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5162779688835144},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.46593207120895386},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45026448369026184},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.42988741397857666},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4274662733078003},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3788885474205017},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.11026665568351746}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.915908694267273},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8770671486854553},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8413625955581665},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7457406520843506},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7234867215156555},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.569308340549469},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5439320802688599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5162779688835144},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.46593207120895386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45026448369026184},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.42988741397857666},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4274662733078003},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3788885474205017},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.11026665568351746},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2020.3017780","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3017780","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09171319.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:adf952f4bea7432c85c92a8d4eebbbd2","is_oa":true,"landing_page_url":"https://doaj.org/article/adf952f4bea7432c85c92a8d4eebbbd2","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 159639-159649 (2020)","raw_type":"article"},{"id":"pmh:oai:irdb.nii.ac.jp:01146:0005782676","is_oa":true,"landing_page_url":"https://naist.repo.nii.ac.jp/records/4225","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"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":"IEEE Access","raw_type":"journal article"},{"id":"pmh:oai:library.naist.jp:10061/14054","is_oa":true,"landing_page_url":"http://hdl.handle.net/10061/14054","pdf_url":null,"source":{"id":"https://openalex.org/S4377196843","display_name":"NAIST Digital Library (Nara Institute of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I75917431","host_organization_name":"Nara Institute of Science and Technology","host_organization_lineage":["https://openalex.org/I75917431"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.3017780","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.3017780","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09171319.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1069223013","display_name":null,"funder_award_id":"JSPS KAKENHI","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1688345242","display_name":null,"funder_award_id":"17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G3459562248","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4636223006","display_name":null,"funder_award_id":"JSPS KAK","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6616750388","display_name":null,"funder_award_id":"JP17H06101","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G696413919","display_name":null,"funder_award_id":"20H05567","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3074656709.pdf","grobid_xml":"https://content.openalex.org/works/W3074656709.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W158722652","https://openalex.org/W605348272","https://openalex.org/W1501669607","https://openalex.org/W1579853615","https://openalex.org/W1600735390","https://openalex.org/W1977500051","https://openalex.org/W2026949629","https://openalex.org/W2076337359","https://openalex.org/W2083205357","https://openalex.org/W2085662862","https://openalex.org/W2099118758","https://openalex.org/W2108772579","https://openalex.org/W2119717200","https://openalex.org/W2136152952","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2395639500","https://openalex.org/W2791590751","https://openalex.org/W2810821963","https://openalex.org/W2892176966","https://openalex.org/W2962776342","https://openalex.org/W2963068985","https://openalex.org/W2963246392","https://openalex.org/W2997290921","https://openalex.org/W4233299515","https://openalex.org/W4283815751","https://openalex.org/W6630073874","https://openalex.org/W6634817459","https://openalex.org/W6635800190","https://openalex.org/W6676255796","https://openalex.org/W6680258741","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6711957290","https://openalex.org/W6839917624"],"related_works":["https://openalex.org/W48079147","https://openalex.org/W2394821827","https://openalex.org/W326836678","https://openalex.org/W2563921006","https://openalex.org/W1963944933","https://openalex.org/W2174703168","https://openalex.org/W2111550420","https://openalex.org/W1977846844","https://openalex.org/W2549666521","https://openalex.org/W3133893348"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,20,77,100,112,115,121,125,128,139,145,152,160,168,180,186],"problem":[3,21],"of":[4,22,117,124,182],"policy":[5,56,75,90,137,158,170],"adaptation":[6,12,57,146],"for":[7,31,63,76,138,159],"reinforcement-learning-based":[8],"dialog":[9,29,55,89],"management.":[10],"Policy":[11],"is":[13,189],"a":[14,27,32,73,88,136,156],"commonly":[15],"used":[16,50],"technique":[17],"to":[18,71,105],"alleviate":[19],"data":[23,184],"sparsity":[24],"when":[25,41,179],"training":[26,95],"goal-oriented":[28],"system":[30],"new":[33,74,157],"task":[34,79,162,188],"(the":[35],"target":[36,78,101,129,140,161,187],"task)":[37],"by":[38,51,96,177],"using":[39],"knowledge":[40],"learning":[42,69,98],"policies":[43,175],"in":[44,54,99,114],"an":[45],"existing":[46,106],"task.":[47,102],"The":[48],"methods":[49],"current":[52],"works":[53],"need":[58],"much":[59,163],"time":[60],"and":[61,127],"effort":[62],"adapting":[64],"because":[65],"they":[66],"use":[67],"reinforcement":[68,97],"algorithms":[70],"train":[72],"from":[80],"scratch.":[81],"In":[82,103,166],"this":[83],"paper,":[84],"we":[85,132],"show":[86,150],"that":[87,151],"can":[91,133],"be":[92],"learned":[93,169],"without":[94],"contrast":[104],"works,":[107],"our":[108],"proposed":[109,153],"method":[110,154],"learns":[111,155],"relation":[113],"form":[116],"probability":[118],"distribution":[119],"between":[120],"action":[122],"sets":[123],"source":[126],"tasks.":[130],"Thus,":[131],"immediately":[134],"derive":[135],"task,":[141],"which":[142],"significantly":[143],"reduces":[144],"time.":[147],"Our":[148],"experiments":[149],"more":[164],"quickly.":[165],"addition,":[167],"achieves":[171],"higher":[172],"performance":[173],"than":[174],"created":[176],"fine-tuning":[178],"amount":[181],"available":[183],"on":[185],"limited.":[190]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
