{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:10:24Z","timestamp":1784099424231,"version":"3.55.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"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":[[2026,5,24]]},"DOI":"10.1109\/icc59461.2026.11587924","type":"proceedings-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T19:38:09Z","timestamp":1784057889000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Latency-aware Human-in-the-Loop Reinforcement Learning for Semantic Communications"],"prefix":"10.1109","author":[{"given":"Peizheng","family":"Li","sequence":"first","affiliation":[{"name":"Toshiba Europe Ltd.,Bristol Research and Innovation Laboratory,U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyi","family":"Lin","sequence":"additional","affiliation":[{"name":"Toshiba Europe Ltd.,Bristol Research and Innovation Laboratory,U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adnan","family":"Aijaz","sequence":"additional","affiliation":[{"name":"Toshiba Europe Ltd.,Bristol Research and Innovation Laboratory,U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2021.9663101"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/EuCNC\/6GSummit60053.2024.10597087"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC62392.2025.11274758"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2919300"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2024.3477331"},{"key":"ref6","article-title":"Reinforcement learning from human feedback","author":"Lambert","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.15348"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CSCN63874.2024.10849728"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS65812.2025.11152855"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref11","first-page":"22","article-title":"Constrained policy optimization","volume-title":"International conference on machine learning. PMLR","author":"Achiam"},{"key":"ref12","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3217511"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2500207"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CSCN60443.2023.10453123"}],"event":{"name":"ICC 2026 - IEEE International Conference on Communications","location":"Glasgow, United Kingdom","start":{"date-parts":[[2026,5,24]]},"end":{"date-parts":[[2026,5,28]]}},"container-title":["ICC 2026 - IEEE International Conference on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11586754\/11586037\/11587924.pdf?arnumber=11587924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T06:47:44Z","timestamp":1784098064000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11587924\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,24]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/icc59461.2026.11587924","relation":{},"subject":[],"published":{"date-parts":[[2026,5,24]]}}}