{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T12:33:09Z","timestamp":1776774789406,"version":"3.51.2"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP21H00895"],"award-info":[{"award-number":["JP21H00895"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3462719","type":"journal-article","created":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T18:53:12Z","timestamp":1726599192000},"page":"142640-142650","source":"Crossref","is-referenced-by-count":4,"title":["A Replaceable Curiosity-Driven Candidate Agent Exploration Approach for Task-Oriented Dialog Policy Learning"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8861-6273","authenticated-orcid":false,"given":"Xuecheng","family":"Niu","sequence":"first","affiliation":[{"name":"Graduate School of Engineering, Tohoku University, Sendai, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8835-7877","authenticated-orcid":false,"given":"Akinori","family":"Ito","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Tohoku University, Sendai, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takashi","family":"Nose","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering, Tohoku University, Sendai, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2225812"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.1997.658989"},{"key":"ref3","first-page":"1","article-title":"Accelerating reinforcement learning with value-conditional state entropy exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1203"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1692-3"},{"key":"ref6","first-page":"1","article-title":"On the importance of exploration for generalization in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.003"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3124466"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.08.024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01849-3"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3376418"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5955"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/1238571"},{"key":"ref16","first-page":"7599","article-title":"Fast active learning for pure exploration in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"M\u00e9nard"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2307\/2333424"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21236\/ADA440280"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054546"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1111\/bmsp.12199"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iSAI-NLP56921.2022.9960278"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cognition.2022.105119"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-023-10213-9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29437"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9639.00061"},{"key":"ref28","article-title":"Microsoft dialogue challenge: Building end-to-end task-completion dialogue systems","author":"Li","year":"2018","journal-title":"arXiv:1807.11125"},{"key":"ref29","article-title":"A user simulator for task-completion dialogues","author":"Li","year":"2016","journal-title":"arXiv:1612.05688"},{"key":"ref30","article-title":"Efficient exploration for dialogue policy learning with BBQ networks & replay buffer spiking","author":"Lipton","year":"2016","journal-title":"arXiv:1608.05081"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1047"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268975"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.621"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10681405.pdf?arnumber=10681405","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T12:56:50Z","timestamp":1728565010000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10681405\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3462719","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}