{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T20:56:30Z","timestamp":1775768190057,"version":"3.50.1"},"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":[{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","award":["EP\/X040518\/1."],"award-info":[{"award-number":["EP\/X040518\/1."]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014013","name":"UK Research and Innovation","doi-asserted-by":"publisher","award":["EP\/Y037421\/1"],"award-info":[{"award-number":["EP\/Y037421\/1"]}],"id":[{"id":"10.13039\/100014013","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Netw. Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lnet.2026.3655578","type":"journal-article","created":{"date-parts":[[2026,1,19]],"date-time":"2026-01-19T20:57:01Z","timestamp":1768856221000},"page":"164-168","source":"Crossref","is-referenced-by-count":0,"title":["Diffusion Policies Reinforcement Learning for Resource Allocation in Open RAN Digital Twin"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1036-8816","authenticated-orcid":false,"given":"Zhizhou","family":"He","sequence":"first","affiliation":[{"name":"6GIC, Institute for Communication Systems, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3284-5086","authenticated-orcid":false,"given":"Mohammad","family":"Shojafar","sequence":"additional","affiliation":[{"name":"6GIC, Institute for Communication Systems, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5716-1396","authenticated-orcid":false,"given":"Chuan Heng","family":"Foh","sequence":"additional","affiliation":[{"name":"6GIC, Institute for Communication Systems, University of Surrey, Guildford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6062-8639","authenticated-orcid":false,"given":"Rahim","family":"Tafazolli","sequence":"additional","affiliation":[{"name":"6GIC, Institute for Communication Systems, University of Surrey, Guildford, U.K."}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOMSTD.0001.2000041"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.003.2200879"},{"key":"ref3","volume-title":"O-RAN: Towards an Open and Smart RAN","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.007.2200555"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3365665"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3359998"},{"key":"ref7","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","author":"Wang","year":"2023","journal-title":"arXiv:2208.06193"},{"key":"ref8","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1190\/geo2023-0676.1"},{"key":"ref10","first-page":"1415","article-title":"Maximum likelihood training of score-based diffusion models","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref11","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. 35th Adv. Neural Inf. Process. Syst.","author":"Fujimoto"},{"key":"ref12","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2019","journal-title":"arXiv:1509.02971"},{"key":"ref13","first-page":"1","article-title":"Double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hasselt"},{"key":"ref14","volume-title":"RAN Intelligent Controller (RIC) Tester","year":"2023"}],"container-title":["IEEE Networking Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8253410\/11411875\/11357509.pdf?arnumber=11357509","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:49:07Z","timestamp":1775764147000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11357509\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/lnet.2026.3655578","relation":{},"ISSN":["2576-3156"],"issn-type":[{"value":"2576-3156","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}