{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:29:08Z","timestamp":1784212148762,"version":"3.55.0"},"reference-count":32,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"18","license":[{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T00:00:00Z","timestamp":1757894400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFA1003304"],"award-info":[{"award-number":["2021YFA1003304"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007836","name":"Zhejiang Provincial Key Laboratory of Multimodal Communication Networks and Intelligent Information Processing, Hangzhou, China","doi-asserted-by":"publisher","award":["2021YFA1003304"],"award-info":[{"award-number":["2021YFA1003304"]}],"id":[{"id":"10.13039\/100007836","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,9,15]]},"DOI":"10.1109\/jiot.2025.3582182","type":"journal-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T13:46:58Z","timestamp":1751032018000},"page":"37190-37202","source":"Crossref","is-referenced-by-count":3,"title":["A Hybrid Reinforcement Learning Framework for Hard-Latency Constrained Resource Scheduling"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5346-1684","authenticated-orcid":false,"given":"Luyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3943-5234","authenticated-orcid":false,"given":"An","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2570-8964","authenticated-orcid":false,"given":"Kexuan","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-2955-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1900287"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1900271"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/NOMS56928.2023.10154267"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Fall49728.2020.9348718"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1700268"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/NTMS.2019.8763780"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685604"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.3040907"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3142430"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1800610"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2010.5506265"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WPMC.2014.7014905"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCChina.2012.6356950"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761721"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685777"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422088"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICTC46691.2019.8939680"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3206035"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2005.855401"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.880064"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1160633.1160762"},{"key":"ref23","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref24","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref25","first-page":"1","article-title":"Finite-sample analysis for Sarsa with linear function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zou"},{"key":"ref26","first-page":"1","article-title":"A convergent form of approximate policy iteration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"15","author":"Perkins"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2019.2925601"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3158737"},{"key":"ref29","article-title":"Study on channel model for frequencies from 0.5 to 100GHz, Version 14.3.0","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON58879.2023.10322371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3062457"},{"key":"ref32","first-page":"820","article-title":"Low complexity multiuser MIMO scheduling for weighted sum rate maximization","volume-title":"Proc. 22nd Eur. Signal Process. Conf. (EUSIPCO)","author":"Venkatraman"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11153580\/11053968.pdf?arnumber=11053968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T05:26:50Z","timestamp":1757482010000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11053968\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,15]]},"references-count":32,"journal-issue":{"issue":"18"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3582182","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,15]]}}}