{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T07:31:30Z","timestamp":1767598290223,"version":"3.37.3"},"reference-count":48,"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\/501100004184","name":"Northeastern University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004184","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\/robio54168.2021.9739342","type":"proceedings-article","created":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T21:20:39Z","timestamp":1648502439000},"page":"558-563","source":"Crossref","is-referenced-by-count":3,"title":["Review on Reinforcement Learning Controller in Soft Manipulator"],"prefix":"10.1109","author":[{"given":"Shuopeng","family":"Wang","sequence":"first","affiliation":[{"name":"Northeastern University,School of Mechanical Engineering & Automation,Shenyang,China,110819"}]},{"given":"Rixin","family":"Wang","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Mechanical Engineering & Automation,Shenyang,China,110819"}]},{"given":"Meng","family":"Liu","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Mechanical Engineering & Automation,Shenyang,China,110819"}]},{"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Mechanical Engineering & Automation,Shenyang,China,110819"}]},{"given":"Lina","family":"Hao","sequence":"additional","affiliation":[{"name":"Northeastern University,School of Mechanical Engineering & Automation,Shenyang,China,110819"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICACI.2016.7449855"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920979367"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2016.1540"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793653"},{"article-title":"Elastica: A compliant mechanics environment for soft robotic control","year":"2020","author":"naughton","key":"ref31"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/RoboSoft48309.2020.9116003"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206123"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2734247"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s41315-019-00101-7"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.2975232"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399446"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s42235-020-0102-8"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"1033","DOI":"10.1109\/TRO.2011.2160469","article-title":"Statics and Dynamics of Continuum Robots With General Tendon Routing and External Loading","volume":"27","author":"rucker","year":"2011","journal-title":"IEEE Trans Robot"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3055339"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.201900171"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2016.0065"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794191"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1088\/1748-3190\/aa839f"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2016.2636360"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0246102"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref19"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3056903"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aar3449"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.01.077"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1089\/soro.2019.0082"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/act9040142"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2018.2878318"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1088\/1748-3190\/abe54c"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919893438"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41578-018-0022-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2016.00069"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1088\/1361-665X\/abc26e"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14543"},{"key":"ref46","article-title":"PILCO: A Model-Based and Data-Efficient Approach to Policy Search","author":"deisenroth","year":"2011","journal-title":"presented at the Proceedings of the 28th International Conference on Machine Learning ICML 2011"},{"article-title":"Modern Deep Reinforcement Learning Algorithms","year":"2019","author":"ivanov","key":"ref20"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2958211"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341462"},{"key":"ref22","article-title":"Deep Reinforcement Learning with Double Q-learning","author":"hasselt","year":"2015","journal-title":"Computer ence"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202137"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ISIE.2006.295612"},{"key":"ref24","first-page":"9","article-title":"Deterministic Policy Gradient Algorithms","author":"silver","year":"0"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/su11236751"},{"key":"ref23","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"Computer ence"},{"key":"ref44","first-page":"27836492098785","article-title":"c","author":"ibarz","year":"2021","journal-title":"Int J Robot Res"},{"article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","year":"2018","author":"haamoja","key":"ref26"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-018-0313-5"},{"key":"ref25","article-title":"Asynchronous Methods for Deep Reinforcement Learning","author":"mnih","year":"2016","journal-title":"ArXivl60201783 Cs"}],"event":{"name":"2021 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2021,12,27]]},"location":"Sanya, China","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\/09739342.pdf?arnumber=9739342","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T02:19:51Z","timestamp":1657333191000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9739342\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,27]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/robio54168.2021.9739342","relation":{},"subject":[],"published":{"date-parts":[[2021,12,27]]}}}