{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T16:20:39Z","timestamp":1783614039863,"version":"3.55.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB3305600"],"award-info":[{"award-number":["2022YFB3305600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62141604"],"award-info":[{"award-number":["62141604"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62003015"],"award-info":[{"award-number":["62003015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2024.3487219","type":"journal-article","created":{"date-parts":[[2024,11,5]],"date-time":"2024-11-05T18:38:24Z","timestamp":1730831904000},"page":"8630-8644","source":"Crossref","is-referenced-by-count":14,"title":["Hierarchical Reinforcement Learning for Swarm Confrontation With High Uncertainty"],"prefix":"10.1109","volume":"22","author":[{"given":"Qizhen","family":"Wu","sequence":"first","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4328-6339","authenticated-orcid":false,"given":"Kexin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1859-384X","authenticated-orcid":false,"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"Advanced Research Institute of Multidisciplinary Sciences and the State Key Laboratory of CNS\/ATM, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0275-8387","authenticated-orcid":false,"given":"Jinhu","family":"L\u00fc","sequence":"additional","affiliation":[{"name":"School of Automation Science and Electrical Engineering, Beihang University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.adn6642"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3236805"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2023.3288077"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3250819"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2023.3346815"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3360282"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2022.3158279"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3129504"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03840-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3285223"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2022.03.006"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06419-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.adi8022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1111\/jcal.12451"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2024.3371250"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3237665"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00433-9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tase.2024.3358894"},{"key":"ref20","first-page":"3540","article-title":"Feudal networks for hierarchical reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Vezhnevets"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892507"},{"key":"ref22","first-page":"23609","article-title":"A hierarchical reinforcement learning based optimization framework for large-scale dynamic pickup and delivery problems","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ma"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2021.3119689"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SMC42975.2020.9283173"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05293-5"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/3360116"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1049\/cth2.12413"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3071531"},{"issue":"1122","key":"ref29","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst.","volume":"32","author":"Janner"},{"key":"ref30","first-page":"8234","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst.","volume":"31","author":"Buckman"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2022.3163447"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2022.3194349"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2022.3184427"},{"key":"ref35","first-page":"10835","article-title":"Scaling laws for reward model overoptimization","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","author":"Gao"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3068952"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2023.114016"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1093\/jcde\/qwad020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3096997"},{"key":"ref40","first-page":"4759","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Chua"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10744028.pdf?arnumber=10744028","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T04:43:38Z","timestamp":1743223418000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10744028\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3487219","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}