{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T09:05:10Z","timestamp":1758272710587,"version":"3.37.3"},"reference-count":19,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,3,1]],"date-time":"2021-03-01T00:00:00Z","timestamp":1614556800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Huawei Canada Company Ltd."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Wireless Commun. Lett."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/lwc.2020.3036094","type":"journal-article","created":{"date-parts":[[2020,11,5]],"date-time":"2020-11-05T20:28:07Z","timestamp":1604608087000},"page":"512-516","source":"Crossref","is-referenced-by-count":2,"title":["Learning Power Control From a Fixed Batch of Data"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1607-3875","authenticated-orcid":false,"given":"Mohammad G.","family":"Khoshkholgh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4776-9354","authenticated-orcid":false,"given":"Halim","family":"Yanikomeroglu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume":"48","author":"duan","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2921159"},{"key":"ref12","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref13","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","author":"sohn","year":"2015","journal-title":"Proc Conf Neural Inf Process Syst (NIPS)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904352"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2945774"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2825444"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref17"},{"key":"ref18","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017","journal-title":"Proc Workshop Neural Inf Process Syst (NIPS-W)"},{"year":"2010","key":"ref19","article-title":"Technical specification group radio access network; evolved universal terrestrial radio access (E-UTRA); further advancements for E-UTRA physical layer aspects (release 9)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761431"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2147784"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2945951"},{"key":"ref8","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2928837"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"journal-title":"Reinforcement Learning An Introduction","year":"2017","author":"sutton","key":"ref1"},{"key":"ref9","first-page":"1582","article-title":"Addressing function approximation error in actor–critic methods","author":"fujimoto","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"}],"container-title":["IEEE Wireless Communications Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962382\/9373029\/09249408.pdf?arnumber=9249408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:17Z","timestamp":1652194397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9249408\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":19,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lwc.2020.3036094","relation":{},"ISSN":["2162-2337","2162-2345"],"issn-type":[{"type":"print","value":"2162-2337"},{"type":"electronic","value":"2162-2345"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}