{"id":"https://openalex.org/W4402569707","doi":"https://doi.org/10.1109/access.2024.3462719","title":"A Replaceable Curiosity-Driven Candidate Agent Exploration Approach for Task-Oriented Dialog Policy Learning","display_name":"A Replaceable Curiosity-Driven Candidate Agent Exploration Approach for Task-Oriented Dialog Policy Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402569707","doi":"https://doi.org/10.1109/access.2024.3462719"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3462719","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3462719","pdf_url":null,"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://doi.org/10.1109/access.2024.3462719","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102808021","display_name":"Xuecheng Niu","orcid":"https://orcid.org/0009-0006-8861-6273"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xuecheng Niu","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Sendai, Japan"],"raw_orcid":"https://orcid.org/0009-0006-8861-6273","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Sendai, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082389304","display_name":"Akinori Ito","orcid":"https://orcid.org/0000-0002-8835-7877"},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akinori Ito","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Sendai, Japan"],"raw_orcid":"https://orcid.org/0000-0002-8835-7877","affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Sendai, Japan","institution_ids":["https://openalex.org/I201537933"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109012739","display_name":"Takashi Nose","orcid":null},"institutions":[{"id":"https://openalex.org/I201537933","display_name":"Tohoku University","ror":"https://ror.org/01dq60k83","country_code":"JP","type":"education","lineage":["https://openalex.org/I201537933"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nose","raw_affiliation_strings":["Graduate School of Engineering, Tohoku University, Sendai, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Engineering, Tohoku University, Sendai, Japan","institution_ids":["https://openalex.org/I201537933"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I201537933"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.8335,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.77486243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"12","issue":null,"first_page":"142640","last_page":"142650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9483000040054321,"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":0.9483000040054321,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9442999958992004,"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":0.9343000054359436,"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":0.7892996668815613},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.7817255258560181},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7779161930084229},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7281923890113831},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4743451178073883},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.4307730197906494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4027802348136902},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14221641421318054},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09010061621665955},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07200488448143005}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.7892996668815613},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.7817255258560181},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7779161930084229},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7281923890113831},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4743451178073883},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.4307730197906494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4027802348136902},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14221641421318054},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09010061621665955},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07200488448143005},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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":2,"locations":[{"id":"doi:10.1109/access.2024.3462719","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3462719","pdf_url":null,"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:c5d2d6d8d96549f6bc9902efa72d1e0b","is_oa":true,"landing_page_url":"https://doaj.org/article/c5d2d6d8d96549f6bc9902efa72d1e0b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"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 12, Pp 142640-142650 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3462719","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3462719","pdf_url":null,"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":[],"awards":[{"id":"https://openalex.org/G5584391880","display_name":"\u8a71\u8005\u30fb\u5730\u57df\u30fb\u30b9\u30bf\u30a4\u30eb\u30e2\u30fc\u30d5\u30a3\u30f3\u30b0\u97f3\u58f0\u5408\u6210\u306b\u3088\u308b\u5b9f\u74b0\u5883\u30ea\u30b9\u30cb\u30f3\u30b0\u5b66\u7fd2\u652f\u63f4","funder_award_id":"23K21945","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6261062894","display_name":null,"funder_award_id":"JP21H00895","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"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1975244201","https://openalex.org/W1978929923","https://openalex.org/W1995875735","https://openalex.org/W2117989772","https://openalex.org/W2139612737","https://openalex.org/W2145339207","https://openalex.org/W2152342063","https://openalex.org/W2798494119","https://openalex.org/W2963043030","https://openalex.org/W2963523627","https://openalex.org/W2997289589","https://openalex.org/W3007852061","https://openalex.org/W3015707918","https://openalex.org/W3044126222","https://openalex.org/W3081661003","https://openalex.org/W3085832734","https://openalex.org/W3088273075","https://openalex.org/W3211583675","https://openalex.org/W3214586773","https://openalex.org/W4214717370","https://openalex.org/W4220747123","https://openalex.org/W4224016353","https://openalex.org/W4240446014","https://openalex.org/W4280510002","https://openalex.org/W4310872311","https://openalex.org/W4388001438","https://openalex.org/W4391505264","https://openalex.org/W4393147279","https://openalex.org/W6731619401","https://openalex.org/W6753556266","https://openalex.org/W6853285914","https://openalex.org/W6853445487"],"related_works":["https://openalex.org/W2500779211","https://openalex.org/W48079147","https://openalex.org/W1963944933","https://openalex.org/W2563921006","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2920931047","https://openalex.org/W337810568"],"abstract_inverted_index":{"Task-oriented":[0],"dialog":[1,80,122,179,206,216,235],"policy":[2,180],"learning":[3],"is":[4,218],"often":[5,26],"formulated":[6],"as":[7],"a":[8,58,107,140,248,256],"Reinforcement":[9],"Learning":[10],"problem":[11],"whose":[12],"rewards":[13],"from":[14,152,233],"the":[15,23,29,67,87,90,97,132,144,149,156,166,174,188,196,203,240],"environment":[16,225],"are":[17,37],"extremely":[18],"sparse,":[19],"which":[20],"means":[21],"that":[22,173],"agent":[24,62,68,109,114,183,244],"will":[25],"not":[27],"find":[28],"reward":[30,99,177],"by":[31],"acting":[32],"randomly.":[33],"Thus,":[34],"exploration":[35,48,63,102,212,245],"techniques":[36],"of":[38,89,159,190,205,253,259,262],"primary":[39],"importance":[40],"when":[41],"solving":[42],"RL":[43],"problems,":[44],"and":[45,73,103,161,201,255],"more":[46],"sophisticated":[47],"methods":[49],"must":[50],"be":[51],"devised.":[52],"In":[53,82,136,208],"this":[54,83,209],"study,":[55],"we":[56,85,138],"propose":[57,139],"replaceable":[59,241],"curiosity-driven":[60,242],"candidate":[61,167,243],"approach":[64,213,246],"to":[65,69,100,111,124,127,147,162,220,223,238],"encourage":[66,221],"balance":[70,101],"action":[71,118,228],"sampling":[72,119],"explore":[74,224],"new":[75],"environments":[76],"without":[77,230],"overly":[78],"violating":[79],"strategies.":[81,236],"framework,":[84],"follow":[86],"employment":[88],"curiosity":[91,98,176],"model":[92],"but":[93],"design":[94],"weight":[95],"for":[96,120,143,214],"exploitation.":[104],"We":[105],"designed":[106,219],"multi-candidate":[108],"mechanism":[110,142,185],"filter":[112],"an":[113,211],"with":[115],"relatively":[116],"balanced":[117,227],"formal":[121],"training":[123,134,160,189],"motivate":[125],"agents":[126,151,222],"escape":[128],"pseudo-optimal":[129],"actions":[130],"in":[131,155],"early":[133],"stage.":[135],"addition,":[137],"replacement":[141,184],"first":[145],"time":[146],"prevent":[148],"elected":[150],"performing":[153],"poorly":[154,191],"later":[157],"stages":[158],"fully":[163],"utilize":[164],"all":[165],"agents.":[168],"The":[169,182],"experimental":[170],"results":[171],"show":[172],"adjustable":[175],"promotes":[178],"convergence.":[181],"effectively":[186],"blocks":[187],"trained":[192],"agents,":[193],"significantly":[194,231],"increasing":[195],"task\u2019s":[197],"average":[198,250,260],"success":[199,251],"rate":[200,252],"reducing":[202],"number":[204,258],"turns.":[207],"research,":[210],"task-oriented":[215],"system":[217],"through":[226],"sampling,":[229],"deviating":[232],"learned":[234],"Compared":[237],"baselines,":[239],"yields":[247],"higher":[249],"0.714":[254],"lower":[257],"turns":[261],"20.6.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-19T19:40:27.379048","created_date":"2025-10-10T00:00:00"}