{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:50:37Z","timestamp":1767340237035},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"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":[[2023,12,4]]},"DOI":"10.1109\/robio58561.2023.10354785","type":"proceedings-article","created":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T19:20:45Z","timestamp":1703272845000},"page":"1-6","source":"Crossref","is-referenced-by-count":2,"title":["Uncertainty in Bayesian Reinforcement Learning for Robot Manipulation Tasks with Sparse Rewards"],"prefix":"10.1109","author":[{"given":"Li","family":"Zheng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanghong","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yahao","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangrui","family":"Bai","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haiyang","family":"He","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Erbao","family":"Dong","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,CAS Key Laboratory of Mechanical Behavior and Design of Materials,Department of Precision Machinery and Precision Instrumentation,Hefei,China,230026"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330933"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2522401"},{"article-title":"Mt-opt: Continuous multi-task robotic reinforcement learning at scale","year":"2021","author":"Kalashnikov","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3191070"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-023-01822-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.029"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref10","first-page":"1613","article-title":"Weight uncertainty in neural network","volume-title":"International conference on machine learning","author":"Blundell"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1989.118274"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045502"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/168304.168306"},{"article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","year":"2018","author":"Plappert","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref16","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"International conference on machine learning","author":"Fujimoto"},{"key":"ref17","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref18"}],"event":{"name":"2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)","start":{"date-parts":[[2023,12,4]]},"location":"Koh\u00a0Samui, Thailand","end":{"date-parts":[[2023,12,9]]}},"container-title":["2023 IEEE International Conference on Robotics and Biomimetics (ROBIO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10354348\/10354529\/10354785.pdf?arnumber=10354785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T22:57:23Z","timestamp":1705100243000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10354785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/robio58561.2023.10354785","relation":{},"subject":[],"published":{"date-parts":[[2023,12,4]]}}}