{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T02:07:01Z","timestamp":1777514821787,"version":"3.51.4"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"21","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2024,11,1]]},"DOI":"10.1109\/jiot.2024.3436110","type":"journal-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T20:52:57Z","timestamp":1722459177000},"page":"35432-35444","source":"Crossref","is-referenced-by-count":28,"title":["TranDRL: A Transformer-Driven Deep Reinforcement Learning Enabled Prescriptive Maintenance Framework"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0285-503X","authenticated-orcid":false,"given":"Yang","family":"Zhao","sequence":"first","affiliation":[{"name":"Singapore Institute of Manufacturing Technology, Agency for Science, Technology and Research, Connexis North Tower, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxi","family":"Yang","sequence":"additional","affiliation":[{"name":"Shenzhen Institute for Advanced Study and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7500-8723","authenticated-orcid":false,"given":"Wenbo","family":"Wang","sequence":"additional","affiliation":[{"name":"Faculty of Mechanical and Electrical Engineering and the Yunnan Key Laboratory of Intelligent Control and Application, Kunming University of Science and Technology, Kunming, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9697-7470","authenticated-orcid":false,"given":"Helin","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7442-7416","authenticated-orcid":false,"given":"Dusit","family":"Niyato","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2018.1444806"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2022.108873"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/PHM.2010.5413482"},{"key":"ref4","first-page":"22184","article-title":"Understanding how encoder-decoder architectures attend","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Aitken"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3109955"},{"key":"ref6","article-title":"Cold-start reinforcement learning with softmax policy gradient","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Ding","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106889"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/0740817X.2013.876126"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2018.09.015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2015.10.025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ymssp.2018.05.050"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113701"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/aic.17489"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1080\/0951192X.2019.1571236"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2018.03.280"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2307\/591267"},{"key":"ref19","first-page":"1","article-title":"Deep reinforcement learning from human preferences","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst.","author":"Christiano"},{"key":"ref20","first-page":"1","article-title":"Reward learning from human preferences and demonstrations in Atari","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst.","author":"Ibarz"},{"key":"ref21","article-title":"Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training","author":"Lee","year":"2021","journal-title":"arXiv:2106.05091"},{"key":"ref22","article-title":"SURF: Semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning","author":"Park","year":"2022","journal-title":"arXiv:2203.10050"},{"key":"ref23","first-page":"27652","article-title":"Non-Markovian reward modelling from trajectory labels via interpretable multiple instance learning","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst.","author":"Early"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1080\/09537280802088733"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/759"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/PHM.2008.4711414"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/PHM.2008.4711422"},{"key":"ref28","article-title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting","author":"Oreshkin","year":"2019","journal-title":"arXiv:1905.10437"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijforecast.2019.07.001"},{"key":"ref30","first-page":"486","article-title":"A theoretical analysis of deep q-learning","volume-title":"Proc. Learn. Dyn. Control","author":"Fan"},{"key":"ref31","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref32","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/10736362\/10616165.pdf?arnumber=10616165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:09:58Z","timestamp":1732666198000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10616165\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"references-count":32,"journal-issue":{"issue":"21"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2024.3436110","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]}}}