{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T14:49:36Z","timestamp":1751899776246,"version":"3.37.3"},"reference-count":25,"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 Co., Ltd."}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Wireless Commun. Lett."],"published-print":{"date-parts":[[2021,3]]},"DOI":"10.1109\/lwc.2020.3045005","type":"journal-article","created":{"date-parts":[[2020,12,15]],"date-time":"2020-12-15T21:18:31Z","timestamp":1608067111000},"page":"659-663","source":"Crossref","is-referenced-by-count":7,"title":["Faded-Experience Trust Region Policy Optimization for Model-Free Power Allocation in Interference Channel"],"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":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn (PMLR)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2928837"},{"key":"ref12","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proc Int Conf Neural Informat Process Syst (NIPS)"},{"key":"ref13","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2147784"},{"key":"ref15","first-page":"4565","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"Proc Int Conf Neural Inform Process Syst (NIPS)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1228716.1228725"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref18","first-page":"1196","article-title":"Evolution-guided policy gradient in reinforcement learning","author":"khadka","year":"2018","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref19","article-title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","author":"pourchot","year":"2019","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2017.8227766"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933969"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761431"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2825444"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2945951"},{"journal-title":"Reinforcement Learning An Introduction","year":"2017","author":"sutton","key":"ref2"},{"key":"ref9","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"journal-title":"Deep Learning","year":"2016","author":"goodfellow","key":"ref1"},{"journal-title":"Attraction-repulsion actor-critic for continuous control reinforcement learning","year":"2019","author":"doan","key":"ref20"},{"key":"ref22","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":"ref21","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref24","article-title":"Automatic differentiation in pytorch","author":"paszke","year":"2017","journal-title":"Proc NIPS-W"},{"year":"2017","key":"ref23","article-title":"5G; Study on channel model for frequencies from 0.5 to 100 GHz, (version 14.0.0 release 14)"},{"journal-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref25"}],"container-title":["IEEE Wireless Communications Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962382\/9373029\/09295396.pdf?arnumber=9295396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:53Z","timestamp":1652194373000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9295396\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3]]},"references-count":25,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/lwc.2020.3045005","relation":{},"ISSN":["2162-2337","2162-2345"],"issn-type":[{"type":"print","value":"2162-2337"},{"type":"electronic","value":"2162-2345"}],"subject":[],"published":{"date-parts":[[2021,3]]}}}