{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T20:13:13Z","timestamp":1778530393011,"version":"3.51.4"},"reference-count":66,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62203349"],"award-info":[{"award-number":["62203349"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Innovation Special Field of China","doi-asserted-by":"publisher","award":["23-TQ01-04-ZT-01-011"],"award-info":[{"award-number":["23-TQ01-04-ZT-01-011"]}],"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":[[2026,5,15]]},"DOI":"10.1109\/jiot.2026.3664048","type":"journal-article","created":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:00:56Z","timestamp":1770930056000},"page":"20675-20691","source":"Crossref","is-referenced-by-count":0,"title":["Safe Reinforcement-Learning-Based Guidance Strategy Against Active Defense Target in Three-Player Engagement"],"prefix":"10.1109","volume":"13","author":[{"given":"Yuting","family":"Shang","sequence":"first","affiliation":[{"name":"School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7364-3101","authenticated-orcid":false,"given":"Yuanli","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5758-4372","authenticated-orcid":false,"given":"Haonan","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0704-2388","authenticated-orcid":false,"given":"Yifan","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-024-09564-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-024-09604-w"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-023-08602-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-021-07142-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-021-06820-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2020.105996"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.2514\/1.g004875"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2514\/1.56924"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2019.105529"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2019.05.011"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/7980379"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2017.06.015"},{"issue":"6","key":"ref13","first-page":"51","article-title":"Integrated strategy of penetration and attack based on optimal control","volume":"40","author":"Wang","year":"2022","journal-title":"Flight Dyn."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2514\/1.g002315"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2023.04.012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2019.12.009"},{"key":"ref17","first-page":"229","volume-title":"Reinforcement Learning: An Introduction","volume":"17","author":"Sutton","year":"1999"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2024.08.031"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace10020133"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2514\/1.i010877"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2024.08.004"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3457538"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tiv.2022.3233592"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2023.3277087"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3084685"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/drones7050332"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2024.109131"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2023.129092"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2024.3491582"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2024.3426326"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3238656"},{"key":"ref32","first-page":"1970","article-title":"Safe control under input limits with neural control barrier functions","volume-title":"Proc. Conf. Robot Learn.","author":"Liu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/lcsys.2022.3229865"},{"issue":"1","key":"ref34","first-page":"6070","article-title":"Risk-constrained reinforcement learning with percentile risk criteria","volume":"18","author":"Chow","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","article-title":"Accelerated primal-dual policy optimization for safe reinforcement learning","author":"Liang","year":"2018","journal-title":"arXiv:1802.06480"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25900"},{"key":"ref37","volume-title":"Low-Switching Primal-Dual Algorithms for Safe Reinforcement Learning","author":"Liu","year":"2025"},{"issue":"385","key":"ref38","first-page":"1","article-title":"Double duality: Variational primal-dual policy optimization for constrained reinforcement learning","volume":"24","author":"Li","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref39","first-page":"280","article-title":"A primal-dual-critic algorithm for offline constrained reinforcement learning","volume-title":"Proc. Int. Conf. Artif. Intell. Stat","author":"Hong"},{"issue":"1","key":"ref40","first-page":"8103","article-title":"A Lyapunov-based approach to safe reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Chow"},{"key":"ref41","first-page":"9133","article-title":"Responsive safety in reinforcement learning by PID Lagrangian methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stooke"},{"key":"ref42","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref43","article-title":"Projection-based constrained policy optimization","author":"Yang","year":"2020","journal-title":"arXiv:2010.03152"},{"key":"ref44","first-page":"17801","article-title":"Constrained offline policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Polosky"},{"key":"ref45","article-title":"Constrained policy optimization via Bayesian world models","author":"As","year":"2022","journal-title":"arXiv:2201.09802"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17272"},{"key":"ref47","first-page":"15338","article-title":"First order constrained optimization in policy space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s001860050035"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25826"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.dt.2023.02.016"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-021-00577-6"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.071"},{"key":"ref53","article-title":"Reinforcement learning and control as probabilistic inference: Tutorial and review","author":"Levine","year":"2018","journal-title":"arXiv:1805.00909"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2009.10.014"},{"key":"ref55","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"Fujimoto","year":"2019","journal-title":"arXiv:1910.01708"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref57","article-title":"Maximum a posteriori policy optimisation","author":"Abdolmaleki","year":"2018","journal-title":"arXiv:1806.06920"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.2514\/1.12545"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2020.105746"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.cja.2023.05.028"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace9080424"},{"key":"ref62","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018","journal-title":"arXiv:1802.09477"},{"key":"ref63","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a atochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref64","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2019.0541"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.2514\/6.2021-1881"}],"container-title":["IEEE Internet of Things Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6488907\/11513275\/11394757.pdf?arnumber=11394757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:48:08Z","timestamp":1778528888000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11394757\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,15]]},"references-count":66,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/jiot.2026.3664048","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]]}}}