{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:26:21Z","timestamp":1774023981655,"version":"3.50.1"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"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":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/globecom38437.2019.9014004","type":"proceedings-article","created":{"date-parts":[[2020,2,28]],"date-time":"2020-02-28T09:59:24Z","timestamp":1582883964000},"page":"1-6","source":"Crossref","is-referenced-by-count":17,"title":["Reinforcement Learning for Nested Polar Code Construction"],"prefix":"10.1109","author":[{"given":"Lingchen","family":"Huang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huazi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiqun","family":"Ge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2009.090428"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2009.5205857"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"6562","DOI":"10.1109\/TIT.2013.2272694","article-title":"How to construct polar codes","volume":"59","author":"tal","year":"2013","journal-title":"IEEE Transactions on Information Theory"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2011.6033724"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2012.081512.110872"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2011.6033904"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2013.070213.120789"},{"key":"ref17","article-title":"NR; Multiplexing and channel coding","year":"2019","journal-title":"3GPP TS 38 212"},{"key":"ref18","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref19","author":"wu","year":"2017","journal-title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2908870"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP.2018.8555714"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761286"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2942999"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2040961"},{"key":"ref7","article-title":"Deepcode: Feedback Codes via Deep Learning","author":"kim","year":"2018","journal-title":"Conference on Neural Information Processing Systems"},{"key":"ref2","author":"huang","year":"2019","journal-title":"AI Coding Learning to Construct Error Correction Codes"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2009.2021379"},{"key":"ref20","author":"schulman","year":"2015","journal-title":"Trust region policy optimization"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref21","author":"schulman","year":"2015","journal-title":"High-dimensional continuous control using generalized advantage estimation"},{"key":"ref24","author":"gao","year":"2018","journal-title":"Reinforcement learning from imperfect demonstrations"},{"key":"ref23","author":"zhang","year":"2018","journal-title":"Pretraining Deep Actor-Critic Reinforcement Learning Algorithms With Expert Demonstrations"}],"event":{"name":"GLOBECOM 2019 - 2019 IEEE Global Communications Conference","location":"Waikoloa, HI, USA","start":{"date-parts":[[2019,12,9]]},"end":{"date-parts":[[2019,12,13]]}},"container-title":["2019 IEEE Global Communications Conference (GLOBECOM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8968653\/9013108\/09014004.pdf?arnumber=9014004","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,17]],"date-time":"2022-07-17T21:54:18Z","timestamp":1658094858000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9014004\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/globecom38437.2019.9014004","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}