{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:28:16Z","timestamp":1768282096089,"version":"3.49.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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 Chain","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 Multi-Modal Communication Networks and Intelligent Information Processing, Hangzhou, China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007836","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/twc.2025.3597962","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T18:17:54Z","timestamp":1755627474000},"page":"2639-2653","source":"Crossref","is-referenced-by-count":0,"title":["Context-Aware Constrained Reinforcement Learning-Based Energy-Efficient Power Scheduling for Non-Stationary XR Data Traffic"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2570-8964","authenticated-orcid":false,"given":"Kexuan","family":"Wang","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}]},{"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"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3370441"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/BMSB58369.2023.10211491"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LNET.2023.3286581"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3457540"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2930153"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2010.5506265"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WPMC.2014.7014905"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2004.1354603"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2018.8422088"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3142430"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCChina.2012.6356950"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3158737"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3461963"},{"key":"ref14","first-page":"11393","article-title":"Deep reinforcement learning amidst continual structured non-stationarity","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Xie"},{"key":"ref15","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"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/18.995554"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2717986"},{"key":"ref18","first-page":"7553","article-title":"Constrained reinforcement learning has zero duality gap","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paternain"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/ACC53348.2022.9867805"},{"key":"ref20","article-title":"A primal-dual approach to constrained Markov decision processes","author":"Chen","year":"2021","journal-title":"arXiv:2101.10895"},{"key":"ref21","first-page":"8378","article-title":"Natural policy gradient primal-dual method for constrained Markov decision processes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ding"},{"key":"ref22","first-page":"9133","article-title":"Responsive safety in reinforcement learning by PID Lagrangian methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stooke"},{"key":"ref23","first-page":"3304","article-title":"Provably efficient safe exploration via primal-dual policy optimization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Ding"},{"key":"ref24","article-title":"Cancellation-free regret bounds for Lagrangian approaches in constrained Markov decision processes","author":"M\u00fcller","year":"2023","journal-title":"arXiv:2306.07001"},{"key":"ref25","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"Fujimoto","year":"2019","journal-title":"arXiv:1910.01708"},{"key":"ref26","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref27","article-title":"Projection-based constrained policy optimization","author":"Yang","year":"2020","journal-title":"arXiv:2010.03152"},{"key":"ref28","first-page":"15338","article-title":"First order constrained optimization in policy space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30088"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2043769"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2898760"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2762684"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/AHICI.2009.5340336"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-1023-1_45"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ATNAC.2014.7020879"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17337"},{"key":"ref37","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref38","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018","journal-title":"arXiv:1803.02999"},{"key":"ref39","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rakelly"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121432"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2177770"},{"key":"ref42","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref43","first-page":"10555","article-title":"A finite-time analysis of Q-learning with neural network function approximation","volume-title":"Proc. ICML","author":"Xu"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CDS49703.2020.00051"},{"key":"ref45","article-title":"Statistical inference in mean-field variational Bayes","author":"Han","year":"2019","journal-title":"arXiv:1911.01525"},{"key":"ref46","article-title":"Reward shaping via meta-learning","author":"Zou","year":"2019","journal-title":"arXiv:1901.09330"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3078754"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3079807"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761721"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/BF01581643"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7693\/11298242\/11130650.pdf?arnumber=11130650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:08:46Z","timestamp":1768255726000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11130650\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/twc.2025.3597962","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}