{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:24:31Z","timestamp":1759332271033,"version":"3.44.0"},"reference-count":15,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1109\/robio49542.2019.8961852","type":"proceedings-article","created":{"date-parts":[[2020,1,21]],"date-time":"2020-01-21T14:49:51Z","timestamp":1579618191000},"page":"3019-3024","source":"Crossref","is-referenced-by-count":12,"title":["Control of Space Flexible Manipulator Using Soft Actor-Critic and Random Network Distillation"],"prefix":"10.1109","author":[{"given":"Chen","family":"Yang","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Center for Artificial Intelligence and Robotics,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueqian","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Center for Artificial Intelligence and Robotics,Shenzhen,China,518055"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Liang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref10"},{"key":"ref11","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"article-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","year":"2018","author":"haarnoja","key":"ref12"},{"article-title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","year":"2016","author":"kulkarni","key":"ref13"},{"article-title":"Exploration by Random Network Distillation","year":"2018","author":"burda","key":"ref14"},{"key":"ref15","article-title":"Curiosity-driven exploration by selfsupervised prediction","author":"pathak","year":"2017","journal-title":"International Conference on Machine Learning (ICML)"},{"article-title":"Reinforcement Learning with Deep Energy-Based Policies","year":"2017","author":"haarnoja","key":"ref4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8665049"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IRC.2018.00046"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2013.6580605"},{"key":"ref8","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2018.8665152"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMTMA.2009.556"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281783"},{"key":"ref9","article-title":"Trust Region Policy Optimization","author":"schulman","year":"2015","journal-title":"International Conference on Machine Learning (ICML)"}],"event":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2019,12,6]]},"location":"Dali, China","end":{"date-parts":[[2019,12,8]]}},"container-title":["2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8953068\/8961374\/08961852.pdf?arnumber=8961852","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:23:26Z","timestamp":1755800606000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8961852\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":15,"URL":"https:\/\/doi.org\/10.1109\/robio49542.2019.8961852","relation":{},"subject":[],"published":{"date-parts":[[2019,12]]}}}