{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T15:53:03Z","timestamp":1757778783100,"version":"3.28.0"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1109\/globecom46510.2021.9685617","type":"proceedings-article","created":{"date-parts":[[2022,2,2]],"date-time":"2022-02-02T21:59:04Z","timestamp":1643839144000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Delay-Aware Power Control for Downlink Multi-User MIMO via Constrained Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Chang","family":"Tian","sequence":"first","affiliation":[{"name":"Peking University,State Key Laboratory of Advanced Optical Communication Systems and Networks,Department of Electronics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guan","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"An","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu","family":"Luo","sequence":"additional","affiliation":[{"name":"Peking University,State Key Laboratory of Advanced Optical Communication Systems and Networks,Department of Electronics"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2004.840638"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2017.2695199"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2016.2638914"},{"journal-title":"Introduction to Probability Models","year":"1997","author":"ross","key":"ref13"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref14"},{"key":"ref15","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"0","journal-title":"Advances in neural information processing systems"},{"journal-title":"Subgradient methods","year":"2003","author":"boyd","key":"ref16"},{"key":"ref17","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume":"32","author":"silver","year":"0","journal-title":"Proceedings of the 31th International Conference on Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2993442"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2017.2717986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SAHCN.2016.7733010"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2967243"},{"journal-title":"Constrained Markov Decision Processes","year":"1999","author":"altman","key":"ref6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2264058"},{"journal-title":"Benchmarking Safe Exploration in Deep Reinforcement Learning","year":"2019","author":"ray","key":"ref8"},{"journal-title":"Dynamic Programming and Optimal Control","year":"2005","author":"bertsekas","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2021.3064973"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2682318"},{"key":"ref9","first-page":"22","article-title":"Constrained policy optimization","volume":"70","author":"achiam","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning"}],"event":{"name":"GLOBECOM 2021 - 2021 IEEE Global Communications Conference","start":{"date-parts":[[2021,12,7]]},"location":"Madrid, Spain","end":{"date-parts":[[2021,12,11]]}},"container-title":["2021 IEEE Global Communications Conference (GLOBECOM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9685019\/9685006\/09685617.pdf?arnumber=9685617","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,6]],"date-time":"2022-06-06T20:24:20Z","timestamp":1654547060000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9685617\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/globecom46510.2021.9685617","relation":{},"subject":[],"published":{"date-parts":[[2021,12]]}}}