{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:53:59Z","timestamp":1767207239633,"version":"3.48.0"},"reference-count":14,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"project WITS"},{"name":"VELUX Foundation, Denmark, through the Villum Investigator Grant WATER","award":["37793"],"award-info":[{"award-number":["37793"]}]},{"name":"Horizon Europe Marie Sk\u00c5\u0106odowska-Curie Actions (MSCA) Postdoctoral Fellowships under the Project FOCUS-6G","award":["101202623"],"award-info":[{"award-number":["101202623"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Wireless Commun. Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lwc.2025.3642168","type":"journal-article","created":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:34:06Z","timestamp":1766082846000},"page":"1050-1054","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning-Based Policy Optimization for Heterogeneous Radio Access"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1544-5363","authenticated-orcid":false,"given":"Anup","family":"Mishra","sequence":"first","affiliation":[{"name":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9361-2908","authenticated-orcid":false,"given":"\u010cedomir","family":"Stefanovi\u0107","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6195-4797","authenticated-orcid":false,"given":"Petar","family":"Popovski","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7116-397X","authenticated-orcid":false,"given":"Israel","family":"Leyva-Mayorga","sequence":"additional","affiliation":[{"name":"Department of Electronic Systems, Aalborg University, Aalborg, Denmark"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1701319"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.004.2200532"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF59524.2023.10476965"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3507577"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3238061"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2010.120710.100054"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2018.8580848"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008202821328"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2015.7247486"},{"key":"ref10","article-title":"Coexistence of real-time source reconstruction and broadband services over wireless networks","author":"Mishra","year":"2024","journal-title":"arXiv:2411.13192"},{"key":"ref11","article-title":"Double Q-learning","volume-title":"Advances in Neural Information Processing Systems","volume":"23","author":"Hasselt","year":"2010"},{"key":"ref12","first-page":"1","article-title":"Convergence of Q-learning: A simple proof","author":"Melo","year":"2001","journal-title":"Institute of Systems and Robotics"},{"key":"ref13","first-page":"1","article-title":"Near-optimal time and sample complexities for solving Markov decision processes with a generative model","volume-title":"Proc. NeurIPS","author":"Sidford"},{"key":"ref14","article-title":"A Quantitative Measure of Fairness and Discrimination","volume-title":"Eastern Res. Lab.","author":"Jain","year":"1984"}],"container-title":["IEEE Wireless Communications Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962382\/11304577\/11303578.pdf?arnumber=11303578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:44:57Z","timestamp":1767206697000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11303578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/lwc.2025.3642168","relation":{},"ISSN":["2162-2337","2162-2345"],"issn-type":[{"type":"print","value":"2162-2337"},{"type":"electronic","value":"2162-2345"}],"subject":[],"published":{"date-parts":[[2026]]}}}