{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T17:42:23Z","timestamp":1782409343463,"version":"3.54.5"},"reference-count":36,"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\/501100018537","name":"National Science and Technology Major Project of China","doi-asserted-by":"publisher","award":["2021ZD0114504"],"award-info":[{"award-number":["2021ZD0114504"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62373322"],"award-info":[{"award-number":["62373322"]}],"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":["62303407"],"award-info":[{"award-number":["62303407"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LD22E050007"],"award-info":[{"award-number":["LD22E050007"]}]},{"name":"Innovation and Development Special Fund of Hangzhou Chengxi Sci-Tech Innovation Corridor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tase.2024.3424328","type":"journal-article","created":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T19:21:47Z","timestamp":1721071307000},"page":"5551-5565","source":"Crossref","is-referenced-by-count":15,"title":["Meta Reinforcement Learning of Locomotion Policy for Quadruped Robots With Motor Stuck"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4632-7001","authenticated-orcid":false,"given":"Ci","family":"Chen","sequence":"first","affiliation":[{"name":"State Key Laboratory of Industrial Control and Technology and the Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Li","sequence":"additional","affiliation":[{"name":"DeepRobotics Company, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1393-3040","authenticated-orcid":false,"given":"Haojian","family":"Lu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control and Technology and the Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0981-935X","authenticated-orcid":false,"given":"Yue","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control and Technology and the Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9318-9014","authenticated-orcid":false,"given":"Rong","family":"Xiong","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Industrial Control and Technology and the Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1002\/rob.21839"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3007482"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.1133687"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913499192"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14422"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/AQTR.2008.4588739"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-022-00652-6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2002.807274"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1163\/156855303770558660"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-006-9054-4"},{"key":"ref11","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"Nagabandi","year":"2018","journal-title":"arXiv:1803.11347"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/RCAR54675.2022.9872230"},{"key":"ref13","first-page":"12968","article-title":"Trajectory-wise multiple choice learning for dynamics generalization in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Seo"},{"key":"ref14","article-title":"Reinforcement learning with adaptive curriculum dynamics randomization for fault-tolerant robot control","author":"Okamoto","year":"2021","journal-title":"arXiv:2111.10005"},{"key":"ref15","first-page":"5757","article-title":"Context-aware dynamics model for generalization in model-based reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee"},{"key":"ref16","article-title":"Saving the limping: Fault-tolerant quadruped locomotion via reinforcement learning","author":"Liu","year":"2022","journal-title":"arXiv:2210.00474"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3627676.3627686"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CONTROL.2014.6915192"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechmachtheory.2017.10.011"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161034"},{"key":"ref21","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref22","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref23","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018","journal-title":"arXiv:1803.02999"},{"key":"ref24","first-page":"1","article-title":"Meta-reinforcement learning of structured exploration strategies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Gupta"},{"key":"ref25","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv:1611.02779"},{"key":"ref26","article-title":"A simple neural attentive meta-learner","author":"Mishra","year":"2017","journal-title":"arXiv:1707.03141"},{"key":"ref27","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":"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.","author":"Haarnoja"},{"key":"ref29","article-title":"Opening the black box of deep neural networks via information","author":"Shwartz-Ziv","year":"2017","journal-title":"arXiv:1703.00810"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914532150"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161144"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.107"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref35","article-title":"Randomized ensembled double Q-learning: Learning fast without a model","author":"Chen","year":"2021","journal-title":"arXiv:2101.05982"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9816.003.0008"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/10839176\/10598356.pdf?arnumber=10598356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,10]],"date-time":"2025-03-10T17:51:47Z","timestamp":1741629107000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10598356\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3424328","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}