{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:32:50Z","timestamp":1784820770529,"version":"3.55.0"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci?n","doi-asserted-by":"publisher","award":["PID2020-116329GB-C22"],"award-info":[{"award-number":["PID2020-116329GB-C22"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci?n","doi-asserted-by":"publisher","award":["TEC2016-76465-C2-1- R"],"award-info":[{"award-number":["TEC2016-76465-C2-1- R"]}],"id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministerio de Educaci?n y Formaci?n Profesional","award":["PRX 19\/00429"],"award-info":[{"award-number":["PRX 19\/00429"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/twc.2022.3195570","type":"journal-article","created":{"date-parts":[[2022,8,9]],"date-time":"2022-08-09T20:37:49Z","timestamp":1660077469000},"page":"486-501","source":"Crossref","is-referenced-by-count":48,"title":["Model-Based Reinforcement Learning With Kernels for Resource Allocation in RAN Slices"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1756-0130","authenticated-orcid":false,"given":"Juan J.","family":"Alcaraz","sequence":"first","affiliation":[{"name":"Department of Information Technologies and Communications, Technical University of Cartagena, Cartagena, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6938-1540","authenticated-orcid":false,"given":"Fernando","family":"Losilla","sequence":"additional","affiliation":[{"name":"Department of Information Technologies and Communications, Technical University of Cartagena, Cartagena, Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3671-5190","authenticated-orcid":false,"given":"Andrea","family":"Zanella","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Padova, Padova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2870-4678","authenticated-orcid":false,"given":"Michele","family":"Zorzi","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, University of Padova, Padova, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2815638"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1700268"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2019.2903655"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2019.1800498"},{"key":"ref6","first-page":"2643","article-title":"Bounded kernel-based online learning","volume":"10","author":"Orabona","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600951"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1900024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2019.2924345"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2018.2890235"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959263"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600940"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2922961"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2789294"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904371"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2019.2924471"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2988644"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2881964"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2908306"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2754461"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2913413"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2847610"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2020.3019248"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.05.012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3006502"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2020.3043100"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3072435"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933893"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3090423"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2021.3053612"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2986050"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959185"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2727483"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1002\/ett.4087"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904362"},{"key":"ref36","first-page":"4759","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Chua"},{"key":"ref37","article-title":"Model-based reinforcement learning for atari","author":"Kaiser","year":"2019","journal-title":"arXiv:1903.00374"},{"key":"ref38","volume-title":"5G NR: Architecture, Technology, Implementation, and Operation of 3GPP New Radio Standards","author":"Ahmadi","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref40","volume-title":"Reinforcement Learning and Optimal Control","author":"Bertsekas","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279985"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1214\/009053607000000677"},{"key":"ref43","first-page":"951","article-title":"Ultraconservative online algorithms for multiclass problems","volume":"3","author":"Crammer","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","volume-title":"Evolved Universal Terrestrial Radio Access (E-UTRA); Radio Frequency (RF) System Scenarios","year":"2018"},{"key":"ref45","volume-title":"NS-3 Simulator, LTE Module","year":"2022"},{"key":"ref46","volume-title":"E-UTRA Base Station (BS) Radio Transmission and Reception","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3300061.3345431"},{"key":"ref48","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref49","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref50","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref51","volume-title":"Stable Baselines","author":"Hill","year":"2018"},{"key":"ref52","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Fujimoto"},{"key":"ref53","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref54","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":"ref55","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref56","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Gu"},{"key":"ref57","volume-title":"OpenAI Baselines","author":"Dhariwal","year":"2017"},{"key":"ref58","volume-title":"Keras-RL","author":"Plappert","year":"2016"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7693\/10008384\/09852968.pdf?arnumber=9852968","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T12:13:08Z","timestamp":1706789588000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9852968\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":58,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/twc.2022.3195570","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}