{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:12:58Z","timestamp":1784131978108,"version":"3.55.0"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000287","name":"Royal Academy of Engineering","doi-asserted-by":"publisher","award":["RF1415\\14\\22"],"award-info":[{"award-number":["RF1415\\14\\22"]}],"id":[{"id":"10.13039\/501100000287","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010897","name":"Newton Fund","doi-asserted-by":"publisher","award":["428328486"],"award-info":[{"award-number":["428328486"]}],"id":[{"id":"10.13039\/100010897","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2952411","type":"journal-article","created":{"date-parts":[[2019,11,8]],"date-time":"2019-11-08T21:45:48Z","timestamp":1573249548000},"page":"164533-164543","source":"Crossref","is-referenced-by-count":61,"title":["Distributed Deep Deterministic Policy Gradient for Power Allocation Control in D2D-Based V2V Communications"],"prefix":"10.1109","volume":"7","author":[{"given":"Khoi Khac","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4703-4836","authenticated-orcid":false,"given":"Trung Q.","family":"Duong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ngo Anh","family":"Vien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nhien-An","family":"Le-Khac","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long D.","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref33","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref31","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming Optimization Control"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref36","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX OSDI"},{"key":"ref35","first-page":"1019","article-title":"A theoretically grounded application of dropout in recurrent neural networks","author":"gal","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","article-title":"Cooperative multi-agent control using deep reinforcement learning","author":"gupta","year":"2017","journal-title":"Proc Int Joint Conf Auton Agents Multiagent Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2815626"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2895975"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2018.2867775"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2907252"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2894003"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.4108\/eai.20-3-2018.154369"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.4108\/eai.19-12-2018.156080"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.4108\/eai.13-6-2019.159123"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2017.2703855"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876152"},{"key":"ref28","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2761978"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2897134"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2789304"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2014.2319555"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2913909"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2487365"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2015.2509978"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2868002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2015.2479248"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2879578"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2883669"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2887308"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2900460"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2848294"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2893928"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2930115"},{"key":"ref25","article-title":"Deep learning for physical-layer 5G wireless techniques: Opportunities, challenges and solutions","author":"huang","year":"2019","journal-title":"arXiv 1904 09673"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08894348.pdf?arnumber=8894348","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T17:15:24Z","timestamp":1643303724000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8894348\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2952411","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}