{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T01:21:21Z","timestamp":1774315281289,"version":"3.50.1"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"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":["61973066"],"award-info":[{"award-number":["61973066"]}],"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":["61471110"],"award-info":[{"award-number":["61471110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation of Key Laboratory of Equipment Reliability","award":["WD2C20205500306"],"award-info":[{"award-number":["WD2C20205500306"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tcds.2023.3286465","type":"journal-article","created":{"date-parts":[[2023,6,15]],"date-time":"2023-06-15T13:30:14Z","timestamp":1686835814000},"page":"681-691","source":"Crossref","is-referenced-by-count":8,"title":["Supervised Meta-Reinforcement Learning With Trajectory Optimization for Manipulation Tasks"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1101-3221","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"first","affiliation":[{"name":"Faculty of Robot Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0610-3732","authenticated-orcid":false,"given":"Yunzhou","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Northeastern University, Shenyang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Delong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, The Chinese University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4676-7640","authenticated-orcid":false,"given":"Sonya","family":"Coleman","sequence":"additional","affiliation":[{"name":"School of Computing, Engineering and Intelligent Systems, Ulster University, Coleraine, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5077-0658","authenticated-orcid":false,"given":"Dermot","family":"Kerr","sequence":"additional","affiliation":[{"name":"School of Computing, Engineering and Intelligent Systems, Ulster University, Coleraine, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref2","article-title":"Towards playing full MOBA games with deep reinforcement learning","author":"Ye","year":"2020","journal-title":"arXiv:2011.12692"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2020.2973376"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"ref9","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3050723"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3039859"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2019.2963545"},{"key":"ref13","first-page":"5302","article-title":"Meta-reinforcement learning of structured exploration strategies","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Gupta"},{"key":"ref14","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"Duan","year":"2016","journal-title":"arXiv:1611.02779"},{"key":"ref15","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"70","author":"Finn"},{"key":"ref16","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rakelly"},{"key":"ref17","first-page":"9653","article-title":"Guided meta-policy search","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Mendonca"},{"key":"ref18","first-page":"7482","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","volume-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit.","author":"Kendall"},{"key":"ref19","first-page":"222","article-title":"Iterative linear quadratic regulator design for nonlinear biological movement systems","volume-title":"Proc. ICINCO","author":"Li"},{"key":"ref20","article-title":"Learning to reinforcement learn","author":"Wang","year":"2016","journal-title":"arXiv:1611.05763"},{"key":"ref21","article-title":"A simple neural attentive meta-learner","author":"Mishra","year":"2017","journal-title":"arXiv:1707.03141"},{"key":"ref22","article-title":"Some considerations on learning to explore via meta-reinforcement learning","author":"Stadie","year":"2018","journal-title":"arXiv:1803.01118"},{"key":"ref23","article-title":"On first-order meta-learning algorithms","author":"Nichol","year":"2018","journal-title":"arXiv:1803.02999"},{"key":"ref24","article-title":"ProMP: Proximal meta-policy search","author":"Rothfuss","year":"2018","journal-title":"arXiv:1810.06784"},{"key":"ref25","first-page":"2402","article-title":"Meta-gradient reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref26","first-page":"5405","article-title":"Evolved policy gradients","volume-title":"Proc. 32nd Conf. Neural Inf. Process. Syst.","author":"Houthooft"},{"key":"ref27","first-page":"357","article-title":"One-shot visual imitation learning via meta-learning","volume-title":"Proc. Int. Conf. Robot Learn.","author":"Finn"},{"key":"ref28","article-title":"Enhanced meta reinforcement learning using demonstrations in sparse reward environments","author":"Rengarajan","year":"2022","journal-title":"arXiv:2209.13048"},{"key":"ref29","first-page":"1","article-title":"Guided policy search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Levine"},{"key":"ref30","first-page":"4008","article-title":"Guided policy search via approximate mirror descent","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Montgomery"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref32","first-page":"829","article-title":"Learning complex neural network policies with trajectory optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Levine"},{"key":"ref33","first-page":"1071","article-title":"Learning neural network policies with guided policy search under unknown dynamics","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Levine"},{"key":"ref34","article-title":"Motor skill learning with local trajectory methods","author":"Levine","year":"2014"},{"key":"ref35","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"Theodorou","year":"2010","journal-title":"J. Mach. Learn. Res."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7727"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-4321-0","volume-title":"The Cross-Entropy Method: A Unified Approach to Combinatorial Optimization, Monte-Carlo Simulation, and Machine Learning","volume":"133","author":"Rubinstein","year":"2004"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.218"},{"key":"ref39","first-page":"1907","article-title":"Probabilistic differential dynamic programming","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Pan"},{"key":"ref40","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Deisenroth"},{"key":"ref41","first-page":"703","article-title":"Combining model-based and model-free updates for trajectory-centric reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chebotar"},{"key":"ref42","first-page":"27","volume-title":"Optimal control and planning","author":"Levine","year":"2017"},{"issue":"1","key":"ref43","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref45","article-title":"Meta-SGD: Learning to learn quickly for few-shot learning","author":"Li","year":"2017","journal-title":"arXiv:1707.09835"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref47","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Int. Conf. Robot Learn.","author":"Yu"},{"key":"ref48","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref49","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"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10491577\/10153775.pdf?arnumber=10153775","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T17:40:40Z","timestamp":1759858840000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10153775\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":49,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2023.3286465","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}