{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T06:42:05Z","timestamp":1762497725634,"version":"build-2065373602"},"reference-count":20,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T00:00:00Z","timestamp":1760400000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T00:00:00Z","timestamp":1760400000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005046","name":"Natural Science Foundation of Heilongjiang Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005046","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,14]]},"DOI":"10.1109\/iecon58223.2025.11221157","type":"proceedings-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T18:48:46Z","timestamp":1762454926000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["A Hierarchical Reinforcement Learning Method in Multi-UAV Target-Attacker-Defender Games"],"prefix":"10.1109","author":[{"given":"Xilun","family":"Li","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xubin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yipeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuebo","family":"Yang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhan","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,The Research Institute of Intelligent Control and Systems,Harbin,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3248075"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IECON51785.2023.10311875"},{"issue":"2","key":"ref3","first-page":"8","article-title":"Reinforcement-learning-based multi-uav formation control with collision avoidance","volume":"8","author":"Wu","year":"2025","journal-title":"Flight Control & Detection"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3129504"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IECON55916.2024.10905266"},{"key":"ref6","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"article-title":"Learning graph-enhanced commander-executor for multi-agent navigation","year":"2023","author":"Yang","key":"ref7"},{"volume-title":"Differential Games: A Mathematical Theory with Applications to Optimization, Control and Warfare","year":"1965","author":"Isaacs","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/00207721.2021.1872116"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/app11114948"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/make4010009"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref14","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Vezhnevets"},{"key":"ref15","first-page":"10041","article-title":"Maser: Multi-agent reinforcement learning with subgoals generated from experience replay buffer","volume-title":"International Conference on Machine Learning","author":"Jeon"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8664803"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2023.3333572"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2828088"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110811"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/0167-6377(86)90073-8"}],"event":{"name":"IECON 2025 \u2013 51st Annual Conference of the IEEE Industrial Electronics Society","start":{"date-parts":[[2025,10,14]]},"location":"Madrid, Spain","end":{"date-parts":[[2025,10,17]]}},"container-title":["IECON 2025 \u2013 51st Annual Conference of the IEEE Industrial Electronics Society"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11220977\/11220985\/11221157.pdf?arnumber=11221157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T06:37:23Z","timestamp":1762497443000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11221157\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/iecon58223.2025.11221157","relation":{},"subject":[],"published":{"date-parts":[[2025,10,14]]}}}