{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T20:14:22Z","timestamp":1778530462428,"version":"3.51.4"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T00:00:00Z","timestamp":1778803200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Institute of Information & Communications Technology Planning & Evaluation(IITP) grant funded by the Korea governmen","award":["RS-2025-02219317"],"award-info":[{"award-number":["RS-2025-02219317"]}]},{"name":"National Research Foundation of Korea (NRF) funded by the Ministry of Education","award":["2022R1F1A1074672"],"award-info":[{"award-number":["2022R1F1A1074672"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Internet Things J."],"published-print":{"date-parts":[[2026,5,15]]},"DOI":"10.1109\/jiot.2026.3667218","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:49:03Z","timestamp":1771879743000},"page":"21938-21951","source":"Crossref","is-referenced-by-count":0,"title":["Direction Prediction Error-Prioritized Experience Replay (DPE-PER) for Adversarial UAV Interception Under Partial Observability"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1740-6608","authenticated-orcid":false,"given":"Issaree","family":"Srisomboon","sequence":"first","affiliation":[{"name":"Department of Computer Science, Kookmin University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8431-0097","authenticated-orcid":false,"given":"Sanghwan","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Kookmin University, Seoul, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7784-8_10"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3298292"},{"issue":"13","key":"ref6","doi-asserted-by":"crossref","first-page":"2432","DOI":"10.3390\/electronics13132432","article-title":"Autonomous UAV navigation with adaptive control based on deep reinforcement learning","volume":"13","author":"Yin","year":"2024","journal-title":"Electronics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCASIT62299.2024.10828100"},{"issue":"3","key":"ref8","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.cja.2023.09.033","article-title":"Deep-reinforcement-learning-based UAV autonomous navigation and collision avoidance in unknown environments","volume":"37","author":"Wang","year":"2024","journal-title":"Chin. J. Aeronaut."},{"key":"ref9","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref10","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018","journal-title":"arXiv:1801.01290"},{"key":"ref11","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2019","journal-title":"arXiv:1509.02971"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3148364"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3273164"},{"key":"ref14","article-title":"UAV path planning algorithm based on deep Q-learning to search for a floating lost target in the ocean","volume":"179","author":"Boulares","year":"2024","journal-title":"Robot. Auto. Syst."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3327753"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/app12031618"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3249900"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JISPIN.2023.3334690"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS65942.2025.11007858"},{"key":"ref20","article-title":"Partial observability during DRL for robot control","author":"Meng","year":"2022","journal-title":"arXiv:2209.04999"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/FIT60620.2023.00015"},{"issue":"7","key":"ref22","doi-asserted-by":"crossref","first-page":"309","DOI":"10.3390\/drones8070309","article-title":"A deep reinforcement learning-based intelligent maneuvering strategy for the high-speed UAV pursuit-evasion game","volume":"8","author":"Yan","year":"2024","journal-title":"Drones"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3583620"},{"issue":"11","key":"ref24","doi-asserted-by":"crossref","first-page":"993","DOI":"10.3390\/aerospace12110993","article-title":"Multi-UAV cooperative pursuit planning via communication-aware multi-agent reinforcement learning","volume":"12","author":"Ren","year":"2025","journal-title":"Aerospace"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2023.1302898"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/twc.2023.3260304"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC59610.2024.10817384"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tsc.2024.3466852"},{"issue":"3","key":"ref29","doi-asserted-by":"crossref","first-page":"160","DOI":"10.3390\/drones9030160","article-title":"Deep reinforcement learning-enabled trajectory and bandwidth allocation optimization for UAV-assisted integrated sensing and covert communication","volume":"9","author":"Li","year":"2025","journal-title":"Drones"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1155\/2024\/1809850"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3769426"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/589"},{"key":"ref33","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3375083"},{"key":"ref35","article-title":"Prioritized experience replay-based ddqn for unmanned vehicle path planning","author":"Lipeng","year":"2024","journal-title":"arXiv:2406.17286"},{"key":"ref36","article-title":"Hindsight experience replay","author":"Andrychowicz","year":"2017","journal-title":"arXiv:1707.01495"},{"key":"ref37","article-title":"Competitive experience replay","author":"Liu","year":"2019","journal-title":"arXiv:1902.00528"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6049"},{"key":"ref39","first-page":"1191","article-title":"Dynamic experience replay","volume-title":"Proc. Conf. Robot Learn.","author":"Luo"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3162749"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2577619"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-76153-9_28"},{"key":"ref44","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016","journal-title":"arXiv:1602.01783"},{"key":"ref45","article-title":"Gymnasium: A standard interface for reinforcement learning environments","author":"Towers","year":"2024","journal-title":"arXiv:2407.17032"},{"issue":"268","key":"ref46","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume":"22","author":"Raffin","year":"2021","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11513275\/11408184.pdf?arnumber=11408184","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:48:59Z","timestamp":1778528939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408184\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,15]]},"references-count":46,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2026.3667218","relation":{},"ISSN":["2327-4662","2372-2541"],"issn-type":[{"value":"2327-4662","type":"electronic"},{"value":"2372-2541","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,15]]}}}