{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T05:33:37Z","timestamp":1768282417873,"version":"3.49.0"},"reference-count":46,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Wireless Commun."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/twc.2024.3409669","type":"journal-article","created":{"date-parts":[[2024,6,24]],"date-time":"2024-06-24T16:12:20Z","timestamp":1719245540000},"page":"1-15","source":"Crossref","is-referenced-by-count":1,"title":["Optimization for 6G Wireless Communications With Heterogeneous VR and Non-VR 360\u00b0 Videos: A Differentiated Reinforcement Learning Approach"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6098-5073","authenticated-orcid":false,"given":"Wenhan","family":"Yu","sequence":"first","affiliation":[{"name":"Graduate College, Nanyang Technological University (NTU), Jurong West, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3004-7091","authenticated-orcid":false,"given":"Jun","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10436796"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.3006999"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX.2016.7498964"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2017.8122249"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/10447318.2020.1778351"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2019.1800440"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3015556"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3046242"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.2978187"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2850303"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2014.6847927"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3277286"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3313195"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS54860.2022.00100"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3321439"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2980055.2980056"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241565"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3517018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2844322"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS54832.2022.9812869"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3020400"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933762"},{"key":"ref24","first-page":"1","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3216049"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3201983"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3312220"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3277226"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3191354"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190983"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1601089"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3343104"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP48831.2020.9287065"},{"key":"ref34","first-page":"1","article-title":"Is Q-learning provably efficient?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Jin"},{"key":"ref35","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref36","first-page":"12765","article-title":"Phasic self-imitative reduction for sparse-reward goal-conditioned reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref37","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.35.11.1367"},{"key":"ref39","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref40","first-page":"1","article-title":"Hybrid reward architecture for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Van Seijen"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29695"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2896986"},{"key":"ref43","first-page":"4105","article-title":"CoMic: Complementary task learning & mimicry for reusable skills","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hasenclever"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.01955"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450070"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/MASS56207.2022.00112"}],"container-title":["IEEE Transactions on Wireless Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7693\/11298242\/10570236.pdf?arnumber=10570236","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:11:13Z","timestamp":1768255873000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10570236\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/twc.2024.3409669","relation":{},"ISSN":["1536-1276","1558-2248"],"issn-type":[{"value":"1536-1276","type":"print"},{"value":"1558-2248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}