{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T17:42:33Z","timestamp":1755798153391,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/dyspan60163.2024.10632750","type":"proceedings-article","created":{"date-parts":[[2024,8,19]],"date-time":"2024-08-19T17:25:29Z","timestamp":1724088329000},"page":"331-338","source":"Crossref","is-referenced-by-count":3,"title":["Advancing RAN Slicing with Offline Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Kun","family":"Yang","sequence":"first","affiliation":[{"name":"University of Virginia,Department of Electrical and Computer Engineering,USA"}]},{"given":"Shu-Ping","family":"Yeh","sequence":"additional","affiliation":[{"name":"Intel Corporation,USA"}]},{"given":"Menglei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Intel Corporation,USA"}]},{"given":"Jerry","family":"Sydir","sequence":"additional","affiliation":[{"name":"Intel Corporation,USA"}]},{"given":"Jing","family":"Yang","sequence":"additional","affiliation":[{"name":"The Pennsylvania State University,School of Electrical Engineering and Computer Science,USA"}]},{"given":"Cong","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Virginia,Department of Electrical and Computer Engineering,USA"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/JSTSP.2018.2798164"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/TCOMM.2019.2957482"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/MCOM.2017.1600951"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/COMST.2018.2815638"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TVT.2019.2894695"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1007\/s11276-020-02479-w"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/ICC.2019.8761431"},{"key":"ref8","article-title":"A deep Q-learning method for downlink power allocation in multi-cell networks","author":"Ahmed","year":"2019","journal-title":"arXiv preprint arXiv:1904.13032"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/TWC.2021.3051163"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1109\/IEEECONF59524.2023.10477008"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1109\/INFOCOMWKSHPS50562.2020.9162925"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/WCNC.2017.7925950"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1109\/JSAC.2017.2679660"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1109\/TWC.2019.2893168"},{"doi-asserted-by":"publisher","key":"ref15","DOI":"10.1109\/JSAC.2019.2959185"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/TCOMM.2020.3031930"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/LCOMM.2020.3001227"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ICC45855.2022.9838518"},{"doi-asserted-by":"publisher","key":"ref19","DOI":"10.1109\/PIMRC50174.2021.9569358"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/IEEECONF56349.2022.10051992"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/LCN52139.2021.9524965"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1145\/3485983.3494850"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/TMC.2022.3188013"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1109\/tmc.2022.3188013"},{"key":"ref25","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv preprint arXiv:2005.01643"},{"volume-title":"in International Conference on Learning Representations (ICLR)","author":"Xiong","article-title":"Nearly minimax optimal offline reinforcement learning with linear function approximation: Single-agent MDP and markov game","key":"ref26"},{"volume-title":"in International Conference on Machine Learning (ICML)","author":"Shi","article-title":"Provably efficient offline reinforcement learning with perturbed data sources","key":"ref27"},{"volume-title":"in International Conference on Machine Learning (ICML)","author":"Li","article-title":"Near-optimal conservative exploration in reinforcement learning under episode-wise constraints","key":"ref28"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1109\/tit.2022.3185139"},{"key":"ref30","first-page":"27 395","article-title":"Policy finetuning: Bridging sample-efficient offline and online reinforcement learning","volume":"34","author":"Xie","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"When should we prefer offline reinforcement learning over behavioral cloning?","author":"Kumar","year":"2022","journal-title":"arXiv preprint arXiv:2204.05618"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1109\/WAINA.2018.00098"},{"doi-asserted-by":"publisher","key":"ref33","DOI":"10.1109\/ICOIN50884.2021.9333944"},{"author":"Geng","journal-title":"Internet Engineering Task Force, Internet-Draft draft-geng-netslices-architecture-02 2017","article-title":"Network slicing architecture","key":"ref34"},{"volume-title":"NetworkGym: Democratizing Network AI via Sim-aaS","year":"2023","author":"Zhang","key":"ref35"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1007\/978-3-642-12331-3_2"},{"doi-asserted-by":"publisher","key":"ref37","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref38","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2024 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN)","start":{"date-parts":[[2024,5,13]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,5,16]]}},"container-title":["2024 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10632771\/10632772\/10632750.pdf?arnumber=10632750","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T05:43:27Z","timestamp":1724132607000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10632750\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/dyspan60163.2024.10632750","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}