{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T15:30:23Z","timestamp":1773329423117,"version":"3.50.1"},"reference-count":37,"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":["62103054"],"award-info":[{"award-number":["62103054"]}],"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":["U22B2079"],"award-info":[{"award-number":["U22B2079"]}],"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":["62273049"],"award-info":[{"award-number":["62273049"]}],"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":["U1913211"],"award-info":[{"award-number":["U1913211"]}],"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":["U2013602"],"award-info":[{"award-number":["U2013602"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4232054"],"award-info":[{"award-number":["4232054"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation of National Key Laboratory of Human Factors Engineering","award":["HFNKL2023WW06"],"award-info":[{"award-number":["HFNKL2023WW06"]}]},{"DOI":"10.13039\/501100012236","name":"Beijing Institute of Technology Research Fund Program for Young Scholars","doi-asserted-by":"publisher","award":["XSQD-6120220298"],"award-info":[{"award-number":["XSQD-6120220298"]}],"id":[{"id":"10.13039\/501100012236","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.2024.3352580","type":"journal-article","created":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T18:40:22Z","timestamp":1705603222000},"page":"453-465","source":"Crossref","is-referenced-by-count":9,"title":["Guided Model-Based Policy Search Method for Fast Motor Learning of Robots With Learned Dynamics"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5670-028X","authenticated-orcid":false,"given":"Xiao","family":"Huang","sequence":"first","affiliation":[{"name":"Key Laboratory of Biomimetic Robots and Systems of Chinese Ministry of Education, Advanced Innovation Center for Intelligent Robots and Systems, School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"}]},{"given":"Xingfang","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Biomimetic Robots and Systems of Chinese Ministry of Education, Advanced Innovation Center for Intelligent Robots and Systems, School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"}]},{"given":"Yan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Biomimetic Robots and Systems of Chinese Ministry of Education, Advanced Innovation Center for Intelligent Robots and Systems, School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4973-4122","authenticated-orcid":false,"given":"Jiachen","family":"Hu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Biomimetic Robots and Systems of Chinese Ministry of Education, Advanced Innovation Center for Intelligent Robots and Systems, School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Biomimetic Robots and Systems of Chinese Ministry of Education, Advanced Innovation Center for Intelligent Robots and Systems, School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8133-6312","authenticated-orcid":false,"given":"Zhihong","family":"Jiang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Biomimetic Robots and Systems of Chinese Ministry of Education, Advanced Innovation Center for Intelligent Robots and Systems, School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2022.3231055"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2966818"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2988642"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.3024725"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3084374"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3185071"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3144282"},{"key":"ref10","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proc. 28th Int. Conf. Mach. Learn.","author":"Deisenroth"},{"key":"ref11","first-page":"25","article-title":"Improving PILCO with Bayesian neural network dynamics models","volume-title":"Proc. Data-Efficient Mach. Learn. Workshop (ICML)","volume":"4","author":"Gal"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3184837"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907001"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989202"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2865891"},{"key":"ref17","first-page":"1","article-title":"Plan online, learn offline: Efficient learning and exploration via model-based control","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Lowrey"},{"key":"ref18","article-title":"Model-based value estimation for efficient model-free reinforcement learning","author":"Feinberg","year":"2018","journal-title":"arXiv:1803.00101"},{"key":"ref19","first-page":"1","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Janner"},{"issue":"1","key":"ref20","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2933152"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3389\/fnbeh.2012.00079"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1037\/bne0000116"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.01.014.2008"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00262.2009"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1111\/j.1460-9568.2007.05353.x"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3045574"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2018.2843563"},{"key":"ref30","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gu"},{"key":"ref31","first-page":"4759","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chua"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3192800"},{"key":"ref33","volume-title":"Pybullet, a Python Module for Physics Simulation for Games, Robotics and Machine Learning","author":"Coumans","year":"2016"},{"key":"ref34","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":"ref35","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref36","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593894"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8856\/10839176\/10409121.pdf?arnumber=10409121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T19:14:45Z","timestamp":1737400485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10409121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/tase.2024.3352580","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}