{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T09:55:02Z","timestamp":1740131702681,"version":"3.37.3"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100010665","name":"H2020 Marie Sk\u0142odowska-Curie Actions","doi-asserted-by":"publisher","award":["749798"],"award-info":[{"award-number":["749798"]}],"id":[{"id":"10.13039\/100010665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004359","name":"Vetenskapsr\u00e5det","doi-asserted-by":"publisher","award":["2018-03701"],"award-info":[{"award-number":["2018-03701"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Commun."],"published-print":{"date-parts":[[2020,1]]},"DOI":"10.1109\/tcomm.2019.2951563","type":"journal-article","created":{"date-parts":[[2019,11,5]],"date-time":"2019-11-05T20:36:30Z","timestamp":1572986190000},"page":"645-653","source":"Crossref","is-referenced-by-count":9,"title":["Learning Physical-Layer Communication With Quantized Feedback"],"prefix":"10.1109","volume":"68","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2356-5704","authenticated-orcid":false,"given":"Jinxiang","family":"Song","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5511-4396","authenticated-orcid":false,"given":"Bile","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5155-8018","authenticated-orcid":false,"given":"Christian","family":"Hager","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1298-6159","authenticated-orcid":false,"given":"Henk","family":"Wymeersch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anant","family":"Sahai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LEOSST.2007.4288327"},{"journal-title":"Phase-Modulated Optical Communication Systems","year":"2005","author":"ho","key":"ref32"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2165793"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/e21080760"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ECOC.2017.8345974"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.91.203901"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2013.061913.120713"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/icc.2011.5962741"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOMW.2018.8644250"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2018.8645416"},{"key":"ref12","article-title":"Model-free training of end-to-end communication systems","author":"aoudia","year":"2018","journal-title":"arXiv 1812 05929"},{"key":"ref13","article-title":"Cooperative multi-agent reinforcement learning for low-level wireless communication","author":"de vrieze","year":"2018","journal-title":"arXiv 1801 04541"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2868103"},{"key":"ref15","article-title":"Deep reinforcement learning autoencoder with noisy feedback","author":"goutay","year":"2018","journal-title":"arXiv 1810 05419"},{"key":"ref16","article-title":"Building encoder and decoder with deep neural networks: On the way to reality","author":"kim","year":"2018","journal-title":"arXiv 1808 02401"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/electronics7070122"},{"key":"ref18","article-title":"Low-complexity recurrent neural network-based polar decoder with weight quantization mechanism","author":"teng","year":"2018","journal-title":"arXiv 1810 12154"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ECOC.2018.8535430"},{"key":"ref28","first-page":"4287","article-title":"Learning values across many orders of magnitude","author":"van hasselt","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2784180"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2017.2758370"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ECOC.2018.8535456"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1982.tb04356.x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2018.2865109"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1364\/OE.26.006222"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ECOC.2018.8535453"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2788405"},{"key":"ref9","article-title":"Approximating the void: Learning stochastic channel models from observation with variational generative adversarial networks","author":"o\u2019shea","year":"2018","journal-title":"arXiv 1805 06350"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2017.8227772"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2019.8815398"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref21","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","author":"ng","year":"1999","journal-title":"Proc 16th Int Conf Mach Learn"},{"key":"ref24","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref23"},{"key":"ref26","article-title":"Reproducibility of benchmarked deep reinforcement learning tasks for continuous control","author":"islam","year":"2017","journal-title":"arXiv 1708 04133"},{"key":"ref25","article-title":"Q-Prop: Sample-efficient policy gradient with an off-policy critic","author":"gu","year":"2016","journal-title":"arXiv 1611 02247"}],"container-title":["IEEE Transactions on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/26\/8960485\/08891726.pdf?arnumber=8891726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T13:46:25Z","timestamp":1651067185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8891726\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1]]},"references-count":37,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcomm.2019.2951563","relation":{},"ISSN":["0090-6778","1558-0857"],"issn-type":[{"type":"print","value":"0090-6778"},{"type":"electronic","value":"1558-0857"}],"subject":[],"published":{"date-parts":[[2020,1]]}}}