{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T13:00:13Z","timestamp":1730293213630,"version":"3.28.0"},"reference-count":11,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1109\/robio.2018.8665328","type":"proceedings-article","created":{"date-parts":[[2019,3,19]],"date-time":"2019-03-19T00:01:56Z","timestamp":1552953716000},"page":"518-523","source":"Crossref","is-referenced-by-count":2,"title":["Sparse Reward Based Manipulator Motion Planning by Using High Speed Learning from Demonstrations"],"prefix":"10.1109","author":[{"given":"Guoyu","family":"Zuo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tingting","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"journal-title":"Prioritized experience replay [J]","year":"2015","author":"schaul","key":"ref10"},{"key":"ref6","first-page":"187a","article-title":"Continuous control with deep reinforcement learning","volume":"8","author":"lillicrap","year":"2015","journal-title":"Computer Science"},{"journal-title":"Openai gym [J]","year":"2016","author":"brockman","key":"ref11"},{"journal-title":"Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards","year":"2017","author":"ve?er\u00edk","key":"ref5"},{"key":"ref8","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Advances in neural information processing systems"},{"journal-title":"Overcoming exploration in reinforcement learning with demonstrations","year":"2017","author":"nair","key":"ref7"},{"key":"ref2","first-page":"1","article-title":"A Survey on Deep Reinforcement Learning","volume":"1","author":"quan","year":"2018","journal-title":"Chinese Journal of Computers"},{"journal-title":"Generative Adversarial Imitation Learning","year":"2016","author":"ho","key":"ref9"},{"key":"ref1","first-page":"176","article-title":"A Review of the Space Trajectory Planning of Redundant Manipulator","volume":"10","author":"han","year":"2016","journal-title":"Journal of Mechanical Transmission"}],"event":{"name":"2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2018,12,12]]},"location":"Kuala Lumpur, Malaysia","end":{"date-parts":[[2018,12,15]]}},"container-title":["2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8653250\/8664715\/08665328.pdf?arnumber=8665328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T03:27:49Z","timestamp":1598239669000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8665328\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/robio.2018.8665328","relation":{},"subject":[],"published":{"date-parts":[[2018,12]]}}}