{"id":"https://openalex.org/W4391505264","doi":"https://doi.org/10.1109/access.2024.3376418","title":"Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning","display_name":"Scheduled Curiosity-Deep Dyna-Q: Efficient Exploration for Dialog Policy Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391505264","doi":"https://doi.org/10.1109/access.2024.3376418"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3376418","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3376418","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10468605.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10468605.pdf","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/A5103144936","display_name":"Takashi Nose","orcid":"https://orcid.org/0000-0001-5403-0019"},"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":0.2404,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.59554763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"12","issue":null,"first_page":"46940","last_page":"46952"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12128","display_name":"AI in Service Interactions","score":0.9843000173568726,"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/T12128","display_name":"AI in Service Interactions","score":0.9843000173568726,"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":0.982699990272522,"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":0.9390000104904175,"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":0.928733229637146},{"id":"https://openalex.org/keywords/curiosity","display_name":"Curiosity","score":0.8870776891708374},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49520865082740784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3901810646057129},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3421599268913269},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.27309268712997437},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13014110922813416},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09421378374099731}],"concepts":[{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.928733229637146},{"id":"https://openalex.org/C33435437","wikidata":"https://www.wikidata.org/wiki/Q366791","display_name":"Curiosity","level":2,"score":0.8870776891708374},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49520865082740784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3901810646057129},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3421599268913269},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.27309268712997437},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13014110922813416},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09421378374099731}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2024.3376418","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3376418","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10468605.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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2402.00085","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2402.00085","pdf_url":"https://arxiv.org/pdf/2402.00085","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"pmh:oai:doaj.org/article:ce20b18eb08b46bd9cf33b813651fd2b","is_oa":true,"landing_page_url":"https://doaj.org/article/ce20b18eb08b46bd9cf33b813651fd2b","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 46940-46952 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3376418","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3376418","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10468605.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":null,"license_id":null,"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/G1922625838","display_name":"Development of a virtual classmate for assistance of online course","funder_award_id":"23K20725","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391505264.pdf","grobid_xml":"https://content.openalex.org/works/W4391505264.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W1975244201","https://openalex.org/W2117989772","https://openalex.org/W2145339207","https://openalex.org/W2296073425","https://openalex.org/W2511770992","https://openalex.org/W2798494119","https://openalex.org/W2916772188","https://openalex.org/W2923622379","https://openalex.org/W2936674804","https://openalex.org/W2950695840","https://openalex.org/W2963433587","https://openalex.org/W2963523627","https://openalex.org/W2964107636","https://openalex.org/W2997657234","https://openalex.org/W2998081612","https://openalex.org/W3000757491","https://openalex.org/W3008413595","https://openalex.org/W3034571331","https://openalex.org/W3034623328","https://openalex.org/W3081661003","https://openalex.org/W3085832734","https://openalex.org/W3088273075","https://openalex.org/W3142849873","https://openalex.org/W3174681272","https://openalex.org/W3175095351","https://openalex.org/W4280510002","https://openalex.org/W4285336835","https://openalex.org/W4310151703","https://openalex.org/W4310872311","https://openalex.org/W4312609624","https://openalex.org/W4387880405","https://openalex.org/W6717230150","https://openalex.org/W6730641667","https://openalex.org/W6731619401","https://openalex.org/W6736942654","https://openalex.org/W6753556266","https://openalex.org/W6760278398"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4285676344","https://openalex.org/W3094054656","https://openalex.org/W2123270665","https://openalex.org/W2060310955","https://openalex.org/W4382584175","https://openalex.org/W2284924956","https://openalex.org/W3043413210","https://openalex.org/W2613740288","https://openalex.org/W337810568"],"abstract_inverted_index":{"Training":[0],"task-oriented":[1],"dialog":[2,23,27,87],"agents":[3],"based":[4,79],"on":[5,80],"reinforcement":[6,85],"learning":[7,57,77,86,96,110,122,146],"is":[8],"time-consuming":[9],"and":[10,59,63,100,111,123,136,159,167,185,197],"requires":[11],"a":[12,74,81,130],"large":[13],"number":[14],"of":[15,65,178],"interactions":[16],"with":[17,190],"real":[18],"users.":[19],"How":[20],"to":[21,129,153,181,205],"grasp":[22],"policy":[24],"within":[25],"limited":[26],"experiences":[28],"remains":[29],"an":[30],"obstacle":[31],"that":[32,118,143,187],"makes":[33],"the":[34,55,61,125,134,154,157,176,194,201],"agent":[35],"training":[36,46,50,106,188],"process":[37],"less":[38],"efficient.":[39],"In":[40],"addition,":[41],"most":[42],"previous":[43],"frameworks":[44],"start":[45],"by":[47,119],"randomly":[48],"choosing":[49],"samples,":[51],"which":[52],"differs":[53],"from":[54],"human":[56],"method":[58],"hurts":[60],"efficiency":[62],"stability":[64],"training.":[66],"Therefore,":[67],"we":[68,93,141,173],"propose":[69],"Scheduled":[70],"Curiosity-Deep":[71],"Dyna-Q":[72,90],"(SC-DDQ),":[73],"curiosity-driven":[75],"curriculum":[76,109,145],"framework":[78,127],"state-of-":[82],"the-art":[83],"model-based":[84],"model,":[88],"Deep":[89,137],"(DDQ).":[91],"Furthermore,":[92],"design":[94],"ed":[95,175],"schedules":[97],"for":[98,165],"SC-DDQ":[99,166],"DDQ,":[101],"respectively,":[102],"following":[103],"two":[104],"opposite":[105],"strategies:":[107],"classic":[108],"its":[112],"reverse":[113],"version.":[114],"Our":[115],"results":[116],"show":[117],"introducing":[120],"scheduled":[121],"curiosity,":[124],"new":[126],"leads":[128],"significant":[131],"improvement":[132],"over":[133],"DDQ":[135],"Q-learning":[138],"(DQN).":[139],"Surprisingly,":[140],"found":[142,186],"traditional":[144],"was":[147],"not":[148],"always":[149],"effective.":[150],"Specifically,":[151],"according":[152],"experimental":[155],"results,":[156,172],"easy-first":[158],"difficult-first":[160],"strategies":[161,189],"are":[162],"more":[163],"suitable":[164],"DDQ.":[168],"To":[169],"analyze":[170],"our":[171],"adopt":[174],"entropy":[177,192,199],"sampled":[179],"actions":[180],"depict":[182],"action":[183],"exploration":[184],"high":[191],"in":[193,200],"first":[195],"stage":[196,203],"low":[198],"last":[202],"lead":[204],"better":[206],"performance.":[207]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2024-02-03T00:00:00"}