{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,26]],"date-time":"2025-10-26T15:05:59Z","timestamp":1761491159816,"version":"3.37.3"},"reference-count":23,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Guangdong Provincial Key R&D Programme","award":["2019B010120001"],"award-info":[{"award-number":["2019B010120001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3049860","type":"journal-article","created":{"date-parts":[[2021,1,9]],"date-time":"2021-01-09T22:37:00Z","timestamp":1610231820000},"page":"19916-19925","source":"Crossref","is-referenced-by-count":17,"title":["Ensemble Bootstrapped Deep Deterministic Policy Gradient for Vision-Based Robotic Grasping"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2496-7748","authenticated-orcid":false,"given":"Weiwei","family":"Liu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1754-9879","authenticated-orcid":false,"given":"Linpeng","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Junjie","family":"Cao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7115-5091","authenticated-orcid":false,"given":"Xiaokuan","family":"Fu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4822-8939","authenticated-orcid":false,"given":"Yong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zaisheng","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Yang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"MBMF: Model-based priors for model-free reinforcement learning","author":"bansal","year":"2017","journal-title":"arXiv 1709 03153"},{"key":"ref11","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref13","article-title":"Benchmarking reinforcement learning algorithms on real-world robots","author":"mahmood","year":"2018","journal-title":"arXiv 1809 07731"},{"key":"ref14","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018","journal-title":"Proc Conf Robot Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2018.XIV.009"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593986"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref18","first-page":"345","article-title":"Reinforcement learning algorithm for partially observable Markov decision problems","author":"jaakkola","year":"1995","journal-title":"Proc Adv Neural Inf Process Syst"},{"journal-title":"The Cross-Entropy Method A Unified Approach to Combinatorial Optimization Monte-Carlo Simulation and Machine Learning","year":"2013","author":"rubinstein","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461039"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref6","article-title":"A tutorial on Thompson sampling","author":"russo","year":"2017","journal-title":"arXiv 1707 02038"},{"key":"ref5","first-page":"4026","article-title":"Deep exploration via bootstrapped dqn","author":"osband","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.058"},{"key":"ref9","first-page":"2829","article-title":"Continuous deep Q-learning with model-based acceleration","author":"gu","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref20","first-page":"1","article-title":"Deep Q-learning from demonstrations","author":"hester","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref22","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"journal-title":"Pybullet a python module for physics simulation for games robotics and machine learning","year":"2019","author":"coumans","key":"ref23"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09316755.pdf?arnumber=9316755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T11:26:46Z","timestamp":1643282806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9316755\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3049860","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}