{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T00:46:56Z","timestamp":1785804416504,"version":"3.56.0"},"reference-count":35,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62233011"],"award-info":[{"award-number":["62233011"]}],"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":["62273187"],"award-info":[{"award-number":["62273187"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019005","name":"Young Elite Scientists Sponsorship Program by Tianjin","doi-asserted-by":"publisher","award":["TJSQNTJ-2020-21"],"award-info":[{"award-number":["TJSQNTJ-2020-21"]}],"id":[{"id":"10.13039\/501100019005","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Haihe Lab of ITAI","award":["22HHXCJC00003"],"award-info":[{"award-number":["22HHXCJC00003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2024.3377810","type":"journal-article","created":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T19:44:56Z","timestamp":1711395896000},"page":"2269-2280","source":"Crossref","is-referenced-by-count":22,"title":["Autonomous Landing of the Quadrotor on the Mobile Platform via Meta Reinforcement Learning"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6000-6111","authenticated-orcid":false,"given":"Qianqian","family":"Cao","sequence":"first","affiliation":[{"name":"Institute of Robotics and Automatic Information Systems, the College of Artificial Intelligence, and the Tianjin Key Laboratory of Intelligent Robotics, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5079-1168","authenticated-orcid":false,"given":"Ziyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information Systems, the College of Artificial Intelligence, and the Tianjin Key Laboratory of Intelligent Robotics, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9772-7091","authenticated-orcid":false,"given":"Hai","family":"Yu","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information Systems, the College of Artificial Intelligence, and the Tianjin Key Laboratory of Intelligent Robotics, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7311-8005","authenticated-orcid":false,"given":"Xiao","family":"Liang","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information Systems, the College of Artificial Intelligence, and the Tianjin Key Laboratory of Intelligent Robotics, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3061-2708","authenticated-orcid":false,"given":"Yongchun","family":"Fang","sequence":"additional","affiliation":[{"name":"Institute of Robotics and Automatic Information Systems, the College of Artificial Intelligence, and the Tianjin Key Laboratory of Intelligent Robotics, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3035178"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943034"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2461213"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145514"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SSRR.2017.8088164"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981489"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2927938"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3047728"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3301273"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2930489"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2720851"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/EST.2010.14"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICUAS.2018.8453449"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.2514\/6.2019-0140"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636096"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-018-0891-8"},{"key":"ref17","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn. (CoRL)","author":"Yu"},{"key":"ref18","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rakelly"},{"key":"ref19","first-page":"5307","article-title":"Meta-reinforcement learning of structured exploration strategies","volume-title":"Proc. NIPS","author":"Gupta"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref22","first-page":"1","article-title":"Rapid learning or feature reuse? Towards understanding the effectiveness of Maml","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Raghu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/RCAR54675.2022.9872291"},{"key":"ref24","first-page":"1","article-title":"Deep variational information bottleneck","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Alemi"},{"key":"ref25","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rezende"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114"},{"key":"ref27","article-title":"Meta-reinforcement learning robust to distributional shift via model identification and experience relabeling","author":"Mendonca","year":"2020","journal-title":"arXiv:2006.07178"},{"key":"ref28","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja"},{"key":"ref29","first-page":"3003","article-title":"Efficient reinforcement learning via posterior sampling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Osband"},{"key":"ref30","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Paszke"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-26054-9_23"},{"key":"ref32","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Fujimoto"},{"key":"ref33","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2015.2479878"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8856\/10839176\/10478819.pdf?arnumber=10478819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T06:00:29Z","timestamp":1738821629000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10478819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3377810","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}