{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:20:28Z","timestamp":1778948428920,"version":"3.51.4"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["IEEE Trans. Cogn. Commun. Netw."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tccn.2024.3485648","type":"journal-article","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T17:29:28Z","timestamp":1729790968000},"page":"1738-1751","source":"Crossref","is-referenced-by-count":3,"title":["DDPG-E2E: A Novel Policy Gradient Approach for End-to-End Communication Systems"],"prefix":"10.1109","volume":"11","author":[{"given":"Bolun","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Engineering, University of Warwick, Coventry, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7696-0521","authenticated-orcid":false,"given":"Nguyen","family":"Van Huynh","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Electronics, University of Liverpool, Liverpool, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9528-0863","authenticated-orcid":false,"given":"Dinh","family":"Thai Hoang","sequence":"additional","affiliation":[{"name":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2659-8648","authenticated-orcid":false,"given":"Diep N.","family":"Nguyen","sequence":"additional","affiliation":[{"name":"School of Electrical and Data Engineering, University of Technology Sydney, Sydney, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9485-9216","authenticated-orcid":false,"given":"Quoc-Viet","family":"Pham","sequence":"additional","affiliation":[{"name":"School of Computer Science and Statistics, Trinity College Dublin, The University of Dublin, Dublin 2, Ireland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10436824"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2784180"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/26.141453"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2017.2758370"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904361"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2021.3103339"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2017.7926071"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOMW.2018.8644250"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2970707"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2022.3161936"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/9781119873747"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2868103"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2018.8645416"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933891"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.23919\/WiOPT47501.2019.9144089"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2018.05.018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2019.8815483"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3228648"},{"key":"ref22","first-page":"1","article-title":"Turbo Autoencoder: Deep learning based channel codes for point-to-point communication channels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Jiang"},{"issue":"1","key":"ref23","first-page":"1","article-title":"A brief study of deep reinforcement learning with epsilon-greedy exploration","volume":"11","author":"Paavai Anand","year":"2021","journal-title":"Int. J. Comput. Digit. Syst."},{"key":"ref24","first-page":"2829","article-title":"Continuous deep q-learning with model-based acceleration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gu"},{"key":"ref25","article-title":"A deeper look at experience replay","author":"Zhang","year":"2017","journal-title":"arXiv:1712.01275"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41188-6_12"},{"key":"ref27","first-page":"1","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref28","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2019","journal-title":"arXiv:1509.02971"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.30534\/ijatcse\/2020\/175942020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230320"},{"key":"ref31","article-title":"L2 regularization versus batch and weight normalization","author":"Van Laarhoven","year":"2017","journal-title":"arXiv:1706.05350"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1908.08681"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0020-0255(96)00200-9"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmr.2004.11.004"},{"key":"ref38","article-title":"An overview of gradient descent optimization algorithms","author":"Ruder","year":"2016","journal-title":"arXiv:1609.04747"},{"key":"ref39","article-title":"MATLAB implementation of the 3GPP spatial channel model","author":"Salo","year":"2005"}],"container-title":["IEEE Transactions on Cognitive Communications and Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687307\/11030768\/10734396.pdf?arnumber=10734396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T04:17:44Z","timestamp":1749701864000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10734396\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":39,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tccn.2024.3485648","relation":{},"ISSN":["2332-7731","2372-2045"],"issn-type":[{"value":"2332-7731","type":"electronic"},{"value":"2372-2045","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}