{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:20:52Z","timestamp":1783095652006,"version":"3.54.6"},"reference-count":55,"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":"Guangzhou - The Hong Kong University of Science and Technology (Guangzhou) Joint Funding","award":["2025A03J3883"],"award-info":[{"award-number":["2025A03J3883"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/twc.2026.3660250","type":"journal-article","created":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T21:06:53Z","timestamp":1770757613000},"page":"11593-11608","source":"Crossref","is-referenced-by-count":3,"title":["Improve the Training Efficiency of DRL for Wireless Communication Resource Allocation: The Role of Generative Diffusion Models"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8796-4776","authenticated-orcid":false,"given":"Xinren","family":"Zhang","sequence":"first","affiliation":[{"name":"Internet of Things Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangdong, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8073-8851","authenticated-orcid":false,"given":"Jiadong","family":"Yu","sequence":"additional","affiliation":[{"name":"Internet of Things Thrust, The Hong Kong University of Science and Technology (Guangzhou), Guangdong, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2021.3118441"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3367624"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3287540"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/lwc.2024.3429236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2021.3089876"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3418011"},{"key":"ref7","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref8","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agarwal"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.015.2100177"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3177942"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2024.3382293"},{"key":"ref12","first-page":"21164","article-title":"Provably efficient causal reinforcement learning with confounded observational data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref13","first-page":"32974","article-title":"VRL3: A data-driven framework for visual deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s13198-024-02344-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3277861"},{"key":"ref16","article-title":"Understanding learned reward functions","author":"Michaud","year":"2020","journal-title":"arXiv:2012.05862"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC51575.2020.9345106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3400011"},{"key":"ref19","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2021.09.013"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3086503"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3330999"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2982699"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3274145"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2023.3291689"},{"key":"ref26","article-title":"Planning with diffusion for flexible behavior synthesis","author":"Janner","year":"2022","journal-title":"arXiv:2205.09991"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2025.3566034"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3356178"},{"key":"ref29","article-title":"DiffusionGPT: LLM-driven text-to-image generation system","author":"Qin","year":"2024","journal-title":"arXiv:2401.10061"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3096673"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3188302"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3194953"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2022.3217785"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS61880.2024.10620834"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3159836"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC57788.2023.10233514"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2024.3416443"},{"key":"ref38","first-page":"17981","article-title":"Structured denoising diffusion models in discrete state-spaces","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Austin"},{"key":"ref39","first-page":"12454","article-title":"Argmax flows and multinomial diffusion: Learning categorical distributions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Hoogeboom"},{"key":"ref40","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3380820"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3253905"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3065357"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2024.3352173"},{"key":"ref45","article-title":"Federated prompt-based decision transformer for customized VR services in mobile edge computing system","author":"Zhou","year":"2024","journal-title":"arXiv:2402.09729"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2400176"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1900287"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2019.2919236"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2020.09.009"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2019.2921162"},{"key":"ref51","article-title":"Semantic communications: Principles and challenges","author":"Qin","year":"2021","journal-title":"arXiv:2201.01389"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref53","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3219840"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2745201"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7693\/11298242\/11391481.pdf?arnumber=11391481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:02:17Z","timestamp":1770930137000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11391481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/twc.2026.3660250","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}