{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T23:53:50Z","timestamp":1768002830345,"version":"3.49.0"},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,27]],"date-time":"2021-12-27T00:00:00Z","timestamp":1640563200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,27]],"date-time":"2021-12-27T00:00:00Z","timestamp":1640563200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,27]],"date-time":"2021-12-27T00:00:00Z","timestamp":1640563200000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006180","name":"Technology Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006180","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,27]]},"DOI":"10.1109\/robio54168.2021.9739258","type":"proceedings-article","created":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T21:20:39Z","timestamp":1648502439000},"page":"1508-1512","source":"Crossref","is-referenced-by-count":5,"title":["Industrial Insert Robotic Assembly Based on Model-based Meta-Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Dong","family":"Liu","sequence":"first","affiliation":[{"name":"Dalian University of Technology,Dalian,China,116024"}]},{"given":"Xiaomin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,China,116024"}]},{"given":"Yu","family":"Du","sequence":"additional","affiliation":[{"name":"Dalian Jiaotong University,Dalian,China,116028"}]},{"given":"Dan","family":"Gao","sequence":"additional","affiliation":[{"name":"Tangshan Polytechnic College,Tangshan,China,063299"}]},{"given":"Minghao","family":"Wang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,China,116024"}]},{"given":"Ming","family":"Cong","sequence":"additional","affiliation":[{"name":"Dalian University of Technology,Dalian,China,116024"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ISR.2013.6695699"},{"key":"ref11","article-title":"Reinforcement learning: An introduction","author":"sutton","year":"2018"},{"key":"ref12","first-page":"388","article-title":"A survey on policy search for robotics","volume":"2","author":"deisenroth","year":"2013","journal-title":"Foundations and Trends in Robotics"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref14","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-017-0468-y"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"ref17","article-title":"Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics","volume":"27","author":"levine","year":"2014","journal-title":"NIPS"},{"key":"ref18","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref19","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"International Conference on Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2018.12.015"},{"key":"ref27","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2018.09.008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/SBR.LARS.Robocontrol.2014.53"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2701973.2702705"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943199"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2014.6943202"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2017.12.002"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2001.977187"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2019.101894"},{"key":"ref20","first-page":"4008","article-title":"Guided policy search via approximate mirror descent","volume":"29","author":"montgomery","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202244"},{"key":"ref21","article-title":"Combining model-based and model-free updates for trajectory-centric reinforcement learning","author":"chebotar","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340848"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793506"},{"key":"ref26","article-title":"Learning to adapt in dynamic, real-world environments through meta-reinforcement learning","author":"nagabandi","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"}],"event":{"name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","location":"Sanya, China","start":{"date-parts":[[2021,12,27]]},"end":{"date-parts":[[2021,12,31]]}},"container-title":["2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9739207\/9739208\/09739258.pdf?arnumber=9739258","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T02:19:52Z","timestamp":1657333192000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9739258\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,27]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/robio54168.2021.9739258","relation":{},"subject":[],"published":{"date-parts":[[2021,12,27]]}}}