{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T23:56:48Z","timestamp":1773791808253,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62301599"],"award-info":[{"award-number":["62301599"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2026,2,1]]},"DOI":"10.1109\/jiot.2025.3632475","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:45:24Z","timestamp":1763059524000},"page":"4391-4410","source":"Crossref","is-referenced-by-count":1,"title":["Surpassing the Master: A Joint Channel and Power Jamming Decision-Making Approach Under Imperfect Demonstrations"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3237-7916","authenticated-orcid":false,"given":"Xiang","family":"Peng","sequence":"first","affiliation":[{"name":"School of Information and Navigation, Air Force Engineering University of PLA, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6040-3544","authenticated-orcid":false,"given":"Hua","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Information and Navigation, Air Force Engineering University of PLA, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6340-5749","authenticated-orcid":false,"given":"Zisen","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Information and Navigation, Air Force Engineering University of PLA, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3157-4886","authenticated-orcid":false,"given":"Dan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Navigation, Air Force Engineering University of PLA, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3801-4187","authenticated-orcid":false,"given":"Ning","family":"Rao","sequence":"additional","affiliation":[{"name":"School of Information and Navigation, Air Force Engineering University of PLA, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3296111"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1049\/iet-com.2020.0410"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICICSP48821.2019.8958575"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/3625917"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2024.3377447"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3440324"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2022.3204898"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2024.3397308"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2018.2843374"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2020.2999333"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32388-2_47"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2011.5978424"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.2995661"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2022.3219434"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2024.3374215"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2789466"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2947918"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2024.3373886"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3329529"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3459935"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3025160"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2017.2782726"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2018.2841921"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2017.2747543"},{"issue":"5","key":"ref25","first-page":"1223","article-title":"A dynamic adaptive jamming power allocation method based on deep reinforcement learning","volume":"51","author":"Peng","year":"2023","journal-title":"Acta Electonica Sinica"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3369038"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2024.3418944"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICMCIS.2016.7496544"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/app9071361"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279385"},{"key":"ref31","article-title":"Guarded policy optimization with imperfect online demonstrations","author":"Xue","year":"2023","journal-title":"arXiv:2303.01728"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3152146"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3000303"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2912754"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2871259"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2010.2099222"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3366009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2011.110418"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2884910"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3307950"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3098451"},{"key":"ref43","article-title":"Randomized ensembled double Q-learning: Learning fast without a model","author":"Chen","year":"2021","journal-title":"arXiv:2101.05982"},{"key":"ref44","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref45","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref46","first-page":"1","article-title":"Teacher-student framework: A reinforcement learning approach","volume-title":"Proc. AAMAS Workshop Auto. Robots Multirobot Syst.","author":"Zimmer"},{"key":"ref47","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref48","first-page":"2817","article-title":"Robust adversarial reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pinto"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2910272"},{"key":"ref50","article-title":"Soft actor-critic for discrete action settings","author":"Christodoulou","year":"2019","journal-title":"arXiv:1910.07207"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3373640"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2023.103952"},{"key":"ref53","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Schulman"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11363065\/11244811.pdf?arnumber=11244811","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T06:02:49Z","timestamp":1769493769000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11244811\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,1]]},"references-count":53,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2025.3632475","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,1]]}}}