{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:54:00Z","timestamp":1764356040775,"version":"3.46.0"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"SEU Innovation Capability Enhancement Plan for Doctoral Students","award":["CXJH_SEU 24084"],"award-info":[{"award-number":["CXJH_SEU 24084"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFA1014204"],"award-info":[{"award-number":["2024YFA1014204"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62571112"],"award-info":[{"award-number":["62571112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tsp.2025.3624833","type":"journal-article","created":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T18:01:12Z","timestamp":1761242472000},"page":"4430-4445","source":"Crossref","is-referenced-by-count":0,"title":["Provable Performance Bounds for Digital Twin-Driven Reinforcement Learning in Wireless Networks: A Novel Digital-Twin Bisimulation Metric"],"prefix":"10.1109","volume":"73","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8586-4179","authenticated-orcid":false,"given":"Zhenyu","family":"Tao","sequence":"first","affiliation":[{"name":"National Mobile Communications Research Lab, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9341-8382","authenticated-orcid":false,"given":"Wei","family":"Xu","sequence":"additional","affiliation":[{"name":"National Mobile Communications Research Lab, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0809-8511","authenticated-orcid":false,"given":"Xiaohu","family":"You","sequence":"additional","affiliation":[{"name":"National Mobile Communications Research Lab, Southeast University, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.004.2200482"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904371"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3411800"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3171678"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3239189"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3063822"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3198273"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2200830"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.002.2300564"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2024.3438543"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2024.3366434"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3359009"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3343626"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3377114"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3258143"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3380820"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3340107"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"article-title":"Large vision model-enhanced digital twin with deep reinforcement learning for user association and load balancing in dynamic wireless networks","year":"2024","author":"Tao","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3476430"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3310065"},{"key":"ref22","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"97","author":"Cobbe","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-023-10032-z"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3153175"},{"key":"ref25","first-page":"162","article-title":"Metrics for finite Markov decision processes","volume-title":"Proc. Conf. Uncertainty Artif. Intell. (UAI)","author":"Ferns","year":"2004"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2024.3441574"},{"issue":"7","key":"ref28","article-title":"Transfer learning for reinforcement learning domains: A survey","volume-title":"J. Mach. Learn. Res.","volume":"10","author":"Taylor","year":"2009"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref30","article-title":"Towards a unified theory of state abstraction for MDPs","volume-title":"Proc. Int. Symp. Artif. Intell. Math.","author":"Li","year":"2006"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.17005"},{"key":"ref32","first-page":"4764","article-title":"Towards robust bisimulation metric learning","volume-title":"Proc. Conf. Neural Inf. Process. Syst. (NeurIPS),","volume":"34","author":"Kemertas","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7751"},{"article-title":"Knowledge transfer in Markov decision processes","year":"2006","author":"Phillips","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3279268"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3414428"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3325905"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3395698"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3310058"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3208773"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.6.4.366"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/058"},{"key":"ref46","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML), Ser. Proc. Mach. Learn. Res.","volume":"70","author":"Arjovsky","year":"2017"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.4064\/fm-3-1-133-181"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1137\/10080484X"},{"volume-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming.","year":"2014","author":"Puterman","key":"ref49"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2140\/pjm.1955.5.285"},{"key":"ref51","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-71050-9","volume-title":"Optimal Transport: Old and New","volume":"338","author":"Villani","year":"2009"},{"year":"2022","key":"ref52","article-title":"User Equipment (UE) Conformance Specification; Radio Resource Management (RRM)"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3156615"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/0304-3975(80)90031-6"},{"article-title":"A generalized bisimulation metric of state similarity between Markov decision processes: From theoretical propositions to applications","year":"2025","author":"Tao","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-0865-5_26"},{"year":"2019","key":"ref57","article-title":"Digital Cellular Telecommunications System (Phase 2) (GSM); Universal Mobile Telecommunications System (UMTS); LTE; 5G; 3rd Generation Partnership Project (3GPP)"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/10807692\/11215841.pdf?arnumber=11215841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T18:44:56Z","timestamp":1764355496000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11215841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tsp.2025.3624833","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"type":"print","value":"1053-587X"},{"type":"electronic","value":"1941-0476"}],"subject":[],"published":{"date-parts":[[2025]]}}}