{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T20:10:29Z","timestamp":1780517429309,"version":"3.54.1"},"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"}],"funder":[{"name":"Guangdong Provincial Key Laboratory","award":["2024KSYS023"],"award-info":[{"award-number":["2024KSYS023"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Commun. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tccn.2026.3696628","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T19:55:52Z","timestamp":1779738952000},"page":"8522-8535","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge-Guided Deep Reinforcement Learning for Timely State Estimation in Wireless Embodied Networks"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2439-0800","authenticated-orcid":false,"given":"Jiazheng","family":"Chen","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0193-9784","authenticated-orcid":false,"given":"Changyang","family":"She","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Zheng","sequence":"additional","affiliation":[{"name":"China Greatwall Technology Group Co., Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7000-8129","authenticated-orcid":false,"given":"Bohai","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1922-7283","authenticated-orcid":false,"given":"Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Intelligence Science and Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2025.3599899"},{"key":"ref3","article-title":"Synergetic empowerment: Wireless communications meets embodied intelligence","author":"Liang","year":"2025","journal-title":"arXiv:2509.10481"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2025.3541078"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3647412"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2024.3460078"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2946878"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.887306"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2026.3654380"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.106.2100636"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2014.2363950"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2022.3223224"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3223408"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2019.2959162"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2020.2966671"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110257"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2019.108759"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3282256"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3370101"},{"key":"ref20","first-page":"1017","article-title":"P3O: Policy-on policy-off policy optimization","volume-title":"Proc. 35th Int. Conf. Int. Conf. Mach. Learn.","author":"Fakoor"},{"key":"ref21","first-page":"1","article-title":"Bridging the gap between value and policy based reinforcement learning","volume-title":"Proc. Adv. NeurIPS","author":"Nachum"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3172472"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3225581"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3145105"},{"key":"ref25","article-title":"Directed exploration for reinforcement learning","author":"Guo","year":"2019","journal-title":"arXiv:1906.07805"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2023.3327412"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3277861"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3627531"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2002.804034"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3225163"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3069240"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2043769"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3007070"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3394542"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3179305"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3090741"},{"key":"ref37","first-page":"331","article-title":"Markov decision processes","volume-title":"Handbooks in Operations Research and Management Science","volume":"2","author":"Puterman","year":"1990"},{"key":"ref38","volume":"42","author":"Hern\u00e1ndez-Lerma","year":"2012","journal-title":"Further Topics Discrete-Time Markov Control Processes"},{"key":"ref39","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref40","first-page":"735","article-title":"Continuous-discrete reinforcement learning for hybrid control in robotics","volume-title":"Proc. Conf. Robot Learn.","author":"Neunert"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1080\/09540099108946587"},{"key":"ref42","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33th Int. Conf. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1002\/047174882x"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279415"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2928811"},{"key":"ref46","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"}],"container-title":["IEEE Transactions on Cognitive Communications and Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687307\/11304002\/11535125.pdf?arnumber=11535125","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T19:43:55Z","timestamp":1780515835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11535125\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tccn.2026.3696628","relation":{},"ISSN":["2332-7731","2372-2045"],"issn-type":[{"value":"2332-7731","type":"electronic"},{"value":"2372-2045","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}