{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T19:00:03Z","timestamp":1763665203512,"version":"3.45.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"23","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62501157"],"award-info":[{"award-number":["62501157"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23A20281"],"award-info":[{"award-number":["U23A20281"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012456","name":"National Social Science Fund of China","doi-asserted-by":"publisher","award":["24&ZD189"],"award-info":[{"award-number":["24&ZD189"]}],"id":[{"id":"10.13039\/501100012456","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2025,12,1]]},"DOI":"10.1109\/jiot.2025.3610642","type":"journal-article","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:35:04Z","timestamp":1758044104000},"page":"50852-50867","source":"Crossref","is-referenced-by-count":0,"title":["Joint MCS Adaptation and Beamforming Design for Multiuser MISO Systems: A Constrained Hybrid Deep Reinforcement Learning Approach"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7047-0038","authenticated-orcid":false,"given":"Xiaowen","family":"Ye","sequence":"first","affiliation":[{"name":"College of Photonic and Electronic Engineering, Fujian Normal University, Fuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5646-8679","authenticated-orcid":false,"given":"Yuyi","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Macau University of Science and Technology, Taipa, Macau, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8874-8712","authenticated-orcid":false,"given":"Xianghao","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, City University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5234-9429","authenticated-orcid":false,"given":"Liqun","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2016.2618794"},{"volume-title":"NR: Physics Layer Procedures for Data","year":"2020","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3354197"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tcomm.2024.3486982"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3447779"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/18.335960"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638564"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2563400"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2393837"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2964691"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3191744"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3396389"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3236791"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref14"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref18","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(97)90015-3"},{"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. (NeurIPS)","volume":"33","author":"Ding"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/VETEC.1997.600465"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2003.821107"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2824804"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3099495"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11798"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref29","first-page":"1","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Schaul"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3192053"},{"key":"ref31","first-page":"7553","article-title":"Constrained reinforcement learning has zero duality gap","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Paternain"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2025.3583950"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3542780"},{"volume-title":"Keras: The Python Deep Learning Library","year":"2018","author":"Chollet","key":"ref34"},{"volume-title":"Py-ITPP","year":"2020","author":"Saxena","key":"ref35"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11261327\/11165358.pdf?arnumber=11165358","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T18:43:54Z","timestamp":1763664234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11165358\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":35,"journal-issue":{"issue":"23"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3610642","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"type":"electronic","value":"2327-4662"},{"type":"electronic","value":"2372-2541"}],"subject":[],"published":{"date-parts":[[2025,12,1]]}}}