{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T07:11:31Z","timestamp":1766733091246,"version":"3.40.5"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62225107,62271140,62171474"],"award-info":[{"award-number":["62225107,62271140,62171474"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu","doi-asserted-by":"publisher","award":["BK20240174"],"award-info":[{"award-number":["BK20240174"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2242022k60002"],"award-info":[{"award-number":["2242022k60002"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,24]]},"DOI":"10.1109\/wcnc61545.2025.10978657","type":"proceedings-article","created":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T17:53:33Z","timestamp":1746813213000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Diffusion Model and Digital Twin Enhanced Deep Reinforcement Learning for Radio Resource Management in RAN Slicing"],"prefix":"10.1109","author":[{"given":"Shaowen","family":"Xiong","sequence":"first","affiliation":[{"name":"Southeast University,Nanjing,China,210096"}]},{"given":"Shiwen","family":"He","sequence":"additional","affiliation":[{"name":"Central South University,Changsha,China,410083"}]},{"given":"Guanghui","family":"Chen","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China,210096"}]},{"given":"Cheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China,210096"}]},{"given":"Yongming","family":"Huang","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China,210096"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4257-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2991723"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3195570"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC49053.2021.9417260"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3060514"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3336156"},{"key":"ref7","article-title":"Multi-agent constrained policy optimisation","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. in Neural Inf. Process. Syst."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3400011"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.002.2300564"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3395698"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.133.2200447"},{"key":"ref13","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. of the 35th Inter. Conf. on Mach. Learn.","volume":"80","author":"Haarnoja","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2022.00.191"},{"key":"ref15","first-page":"06","article-title":"Constrained policy optimization","volume-title":"Proc. of the 34th Inter. Conf. on Mach. Learn.","volume":"70","author":"Joshua","year":"2017"},{"key":"ref16","first-page":"9133","article-title":"Responsive safety in reinforcement learning by pid lagrangian methods","volume-title":"Inter. Conf. on Mach. Learn.","author":"Stooke","year":"2020"},{"key":"ref17","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE Wireless Communications and Networking Conference (WCNC)","start":{"date-parts":[[2025,3,24]]},"location":"Milan, Italy","end":{"date-parts":[[2025,3,27]]}},"container-title":["2025 IEEE Wireless Communications and Networking Conference (WCNC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10978109\/10978116\/10978657.pdf?arnumber=10978657","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,10]],"date-time":"2025-05-10T06:34:23Z","timestamp":1746858863000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10978657\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,24]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/wcnc61545.2025.10978657","relation":{},"subject":[],"published":{"date-parts":[[2025,3,24]]}}}