{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T17:23:10Z","timestamp":1783099390282,"version":"3.54.6"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"24","license":[{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-2203239"],"award-info":[{"award-number":["CNS-2203239"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CIF-2148253"],"award-info":[{"award-number":["CIF-2148253"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-2203412"],"award-info":[{"award-number":["CNS-2203412"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2023,12,15]]},"DOI":"10.1109\/jiot.2023.3304969","type":"journal-article","created":{"date-parts":[[2023,8,14]],"date-time":"2023-08-14T17:57:24Z","timestamp":1692035844000},"page":"22331-22340","source":"Crossref","is-referenced-by-count":5,"title":["Scheduling Real-Time Wireless Traffic: A Network-Aided Offline Reinforcement Learning Approach"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2292-125X","authenticated-orcid":false,"given":"Jialin","family":"Wan","sequence":"first","affiliation":[{"name":"Department of ECEE, Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sen","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of ECEE, Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-670X","authenticated-orcid":false,"given":"Zhaofeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of ECEE, Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3840-1753","authenticated-orcid":false,"given":"Junshan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of ECE, University of California at Davis, Davis, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0684-4111","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Communications Technology Laboratory, National Institute of Standards and Technology, Gaithersburg, MD, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2009.5061954"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/1530748.1530772"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2013.2280846"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1860093.1860099"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2010.5462048"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.110508"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2014.2360365"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2746285.2746302"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155504"},{"key":"ref10","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2929120"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2734247"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref16","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref17","article-title":"Sample efficient actor-critic with experience replay","author":"Wang","year":"2016","journal-title":"arXiv:1611.01224"},{"key":"ref18","article-title":"Impact of data normalization on deep neural network for time series forecasting","author":"Bhanja","year":"2018","journal-title":"arXiv:1812.05519"},{"key":"ref19","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"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/687"},{"key":"ref21","first-page":"661","article-title":"Efficient reductions for imitation learning","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Stat.","author":"Ross"},{"key":"ref22","first-page":"2613","article-title":"Double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Hasselt"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref24","first-page":"176","article-title":"Averaged-DQN: Variance reduction and stabilization for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Anschel"},{"key":"ref25","article-title":"Maxmin Q-learning: Controlling the estimation bias of Q-learning","author":"Lan","year":"2020","journal-title":"arXiv:2002.06487"},{"key":"ref26","article-title":"Randomized ensembled double Q-learning: Learning fast without a model","author":"Chen","year":"2021","journal-title":"arXiv:2101.05982"},{"key":"ref27","first-page":"1","article-title":"Sample-efficient deep reinforcement learning via episodic backward update","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lee"},{"key":"ref28","first-page":"1","article-title":"Adaptive ensemble Q-learning: Minimizing estimation bias via error feedback","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Wang"},{"key":"ref29","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref30","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"Jang","year":"2016","journal-title":"arXiv:1611.01144"},{"key":"ref31","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref32","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv:1611.02779"},{"key":"ref33","article-title":"Learning to reinforcement learn","author":"Wang","year":"2016","journal-title":"arXiv:1611.05763"},{"key":"ref34","article-title":"Meta reinforcement learning as task inference","author":"Humplik","year":"2019","journal-title":"arXiv:1905.06424"},{"key":"ref35","article-title":"Meta-reinforcement learning of structured exploration strategies","author":"Gupta","year":"2018","journal-title":"arXiv:1802.07245"},{"key":"ref36","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"Nagabandi","year":"2018","journal-title":"arXiv:1803.11347"},{"key":"ref37","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly"},{"key":"ref38","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6488907\/10353047\/10215347-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6488907\/10353047\/10215347.pdf?arnumber=10215347","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T01:19:59Z","timestamp":1703035199000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10215347\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,15]]},"references-count":39,"journal-issue":{"issue":"24"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2023.3304969","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,15]]}}}