{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T08:39:39Z","timestamp":1768466379805,"version":"3.49.0"},"reference-count":66,"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":"NSFC\/RGC Joint Research Scheme","award":["62261160390\/N_HKUST656\/22"],"award-info":[{"award-number":["62261160390\/N_HKUST656\/22"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471276"],"award-info":[{"award-number":["62471276"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Commun."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tcomm.2025.3631552","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T18:27:32Z","timestamp":1762885652000},"page":"1066-1082","source":"Crossref","is-referenced-by-count":0,"title":["An Efficient Reservation Protocol for Medium Access: When Tree Splitting Meets Reinforcement Learning"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3992-5468","authenticated-orcid":false,"given":"Yutao","family":"Chen","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, the State Key Laboratory of Space Network and Communications, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9066-1448","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, the State Key Laboratory of Space Network and Communications, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1900271"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3063686"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2016.7565189"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3191937"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3145234"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/JCN.2023.000044"},{"key":"ref7","volume-title":"Digital Communications: Fundamentals and Applications","author":"Sklar","year":"2017"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21236\/ad0707853"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1024916.1024920"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1979.1056093"},{"issue":"3","key":"ref11","first-page":"80","article-title":"Random multiple-access stack algorithm","volume":"16","author":"Tsybakov","year":"1980","journal-title":"Problemy Peredachi Informatsii"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1985.1057023"},{"key":"ref13","volume-title":"Data Networks","author":"Bertsekas","year":"1992"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1981.1056332"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056509"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1985.1057014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2009.2013340"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2012.051712.101109"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1975.1092768"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/49.840210"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2017.8254688"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC.2017.8227708"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MedComNet49392.2020.9191491"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3188280"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3281486"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1985.1057022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/18.720543"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2173711"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2017.8006984"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2492579"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2024.3437208"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2007.070808"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2010.2041066"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2005.1498496"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2007.05991"},{"key":"ref37","volume-title":"Artificial Intelligence: A Modern Approach","author":"Russell","year":"2009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_12"},{"key":"ref39","first-page":"141","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"Proc. AAAI Fall Symp.","author":"Hausknecht"},{"key":"ref40","first-page":"2117","article-title":"Deep variational reinforcement learning for POMDPS","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Igl"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.5555\/1630659.1630806"},{"key":"ref42","first-page":"52","article-title":"Planning with incomplete information as heuristic search in belief space","volume-title":"Proc. 5th Int. Conf. Artif. Intell. Planning Syst.","author":"Bonet"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2879433"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933962"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959185"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904329"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3227304"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3142166"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2007.070409"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/360248.360253"},{"key":"ref52","volume-title":"Data Communications and Networking","author":"Forouzan","year":"2013"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/26.31190"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1980.1675630"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MOBIQUITOUS.2005.13"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/49.709455"},{"key":"ref57","first-page":"1641","article-title":"Solving POMDPs: RTDP-bel vs. point-based algorithms","volume-title":"Proc. 21st Int. Joint Conf. Artif. Intell. (IJCAI)","author":"Bonet"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1613\/jair.678"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1287\/moor.12.3.441"},{"key":"ref60","first-page":"1","article-title":"Solving large pomdps using real time dynamic programming","volume-title":"Proc. AAAI Fall Symp. POMDPs","author":"Geffner"},{"key":"ref61","first-page":"1","article-title":"A pomdp extension with belief-dependent rewards","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Araya"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1613\/jair.761"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2022.1331"},{"key":"ref64","volume-title":"Dynamic Programming and Optimal Control","author":"Bertsekas","year":"2012"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50052-9"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/90.893874"}],"container-title":["IEEE Transactions on Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/26\/11320979\/11240172.pdf?arnumber=11240172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:40:27Z","timestamp":1768423227000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11240172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tcomm.2025.3631552","relation":{},"ISSN":["0090-6778","1558-0857"],"issn-type":[{"value":"0090-6778","type":"print"},{"value":"1558-0857","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}