{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T08:06:48Z","timestamp":1761898008141,"version":"3.41.2"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"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":["61991415"],"award-info":[{"award-number":["61991415"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Committee of Science and Technology","award":["23ZR1423500","& ="],"award-info":[{"award-number":["23ZR1423500","& ="]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Veh."],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1109\/tiv.2024.3424859","type":"journal-article","created":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T14:59:12Z","timestamp":1720537152000},"page":"1168-1183","source":"Crossref","is-referenced-by-count":1,"title":["An Adaptive Meta-Reinforcement Learning Algorithm for Simulation to Reality in Dynamic Scene"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9009-0158","authenticated-orcid":false,"given":"Wenwen","family":"Xiao","sequence":"first","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4577-9241","authenticated-orcid":false,"given":"Xiangfeng","family":"Luo","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8016-9310","authenticated-orcid":false,"given":"Shaorong","family":"Xie","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3444-9992","authenticated-orcid":false,"given":"Hang","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2021.10.007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3223131"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIE53562.2021.00055"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3240287"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00261"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109916"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-021-0642-7"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3264038"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.065"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3128521"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118394"},{"key":"ref15","first-page":"507","article-title":"Agent57: Outperforming the atari human benchmark","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Badia","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref17","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref19","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9091363"},{"key":"ref21","article-title":"A review of meta-reinforcement learning for deep neural networks architecture search","volume-title":"CoRR","volume":"abs\/1812.07995","author":"Jaafra","year":"2018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3057046"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3072339"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1561\/2200000086"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794443"},{"key":"ref26","article-title":"Generalizing across domains via cross-gradient training","volume-title":"CoRR","volume":"abs\/1804.10745","author":"Shankar","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00219"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2942989"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01000"},{"key":"ref31","article-title":"Deep reinforcement learning: An overview","volume-title":"CoRR","volume":"abs\/1701.07274","author":"Li","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00442"},{"key":"ref33","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schaul","year":"2016"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636297"},{"key":"ref36","first-page":"8583","article-title":"Planning to explore via self-supervised world models","volume-title":"Int. Conf. Mach. Learn.","author":"Sekar","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117418"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981510"},{"key":"ref39","article-title":"Unity: A general platform for intelligent agents","volume-title":"CoRR","volume":"abs\/1809.02627","author":"Juliani","year":"2018"},{"key":"ref40","article-title":"Randomized ensembled double Q-learning: Learning fast without a model","volume-title":"CoRR","volume":"abs\/2101.05982","author":"Chen","year":"2021"},{"key":"ref41","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly","year":"2019"},{"key":"ref42","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.","author":"Haarnoja","year":"2018"},{"key":"ref43","first-page":"5405","article-title":"Evolved policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Houthooft","year":"2018"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref45","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3127574"}],"container-title":["IEEE Transactions on Intelligent Vehicles"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274857\/11104066\/10591730.pdf?arnumber=10591730","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T04:54:16Z","timestamp":1753937656000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10591730\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":46,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tiv.2024.3424859","relation":{},"ISSN":["2379-8904","2379-8858"],"issn-type":[{"type":"electronic","value":"2379-8904"},{"type":"print","value":"2379-8858"}],"subject":[],"published":{"date-parts":[[2025,2]]}}}