{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:07:35Z","timestamp":1784851655418,"version":"3.55.0"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,7,1]],"date-time":"2023-07-01T00:00:00Z","timestamp":1688169600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Singapore Ministry of Education Academic Research Fund","award":["Tier 1 RG90\/22"],"award-info":[{"award-number":["Tier 1 RG90\/22"]}]},{"name":"Singapore Ministry of Education Academic Research Fund","award":["RG97\/20"],"award-info":[{"award-number":["RG97\/20"]}]},{"name":"Singapore Ministry of Education Academic Research Fund","award":["Tier 1 RG24\/20"],"award-info":[{"award-number":["Tier 1 RG24\/20"]}]},{"name":"Singapore Ministry of Education Academic Research Fund","award":["Tier 2 MOE2019-T2-1-176"],"award-info":[{"award-number":["Tier 2 MOE2019-T2-1-176"]}]},{"name":"Nanyang Technological University-Wallenberg AI, Autonomous Systems and Software Program (WASP) Joint Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1109\/jsac.2023.3280988","type":"journal-article","created":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T17:23:41Z","timestamp":1685467421000},"page":"2138-2157","source":"Crossref","is-referenced-by-count":39,"title":["Asynchronous Hybrid Reinforcement Learning for Latency and Reliability Optimization in the Metaverse Over Wireless Communications"],"prefix":"10.1109","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6098-5073","authenticated-orcid":false,"given":"Wenhan","family":"Yu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Terence Jie","family":"Chua","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3004-7091","authenticated-orcid":false,"given":"Jun","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2835558"},{"key":"ref12","first-page":"5398","article-title":"Hybrid reward architecture for reinforcement learning","volume":"30","author":"van seijen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2725519"},{"key":"ref15","article-title":"Wireless extended reality (XR): Challenges and new research directions","author":"akyildiz","year":"0","journal-title":"ITU J Future Evol Technol"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2896986"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1900271"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1051\/ro\/2018036"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref30","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800418"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2014.2372852"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417805"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2014.2316834"},{"key":"ref2","year":"2021","journal-title":"Framing the Future of Web 3 0 METAVERSE EDITION"},{"key":"ref1","article-title":"Multi-agent deep reinforcement learning for digital twin over 6G wireless communication in the metaverse","author":"yu","year":"2023","journal-title":"Proc IEEE INFOCOM PerAI-6G Workshop"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.130.2200510"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/2669533"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2841349"},{"key":"ref38","first-page":"1","article-title":"Trajectory design and generalization for UAV enabled networks: A deep reinforcement learning approach","author":"li","year":"2020","journal-title":"Proc IEEE Wireless Commun Netw Conf (WCNC)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2895593"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2005.1421925"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3156756"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3035391"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2981434"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2791598"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2898573"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2020.2981266"},{"key":"ref47","article-title":"Is Q-learning provably efficient","author":"jin","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2848295"},{"key":"ref42","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref41","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2960631"},{"key":"ref44","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.3018159"},{"key":"ref43","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3020400"},{"key":"ref29","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","year":"0","journal-title":"Meta Quest 2 Our Most Advanced New All-in-One VR Headset"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3221993"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2922285"},{"key":"ref4","article-title":"All one needs to know about metaverse: A complete survey on technological singularity, virtual ecosystem, and research agenda","author":"lee","year":"2021","journal-title":"arXiv 2110 05352"},{"key":"ref3","author":"grider","year":"2021","journal-title":"THE METAVERSE web 3 0 Virtudal Cloud Economies"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01534"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2954885"},{"key":"ref40","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/10173687\/10138588.pdf?arnumber=10138588","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,24]],"date-time":"2023-07-24T17:48:58Z","timestamp":1690220938000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10138588\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7]]},"references-count":47,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2023.3280988","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"value":"0733-8716","type":"print"},{"value":"1558-0008","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7]]}}}