{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T12:45:41Z","timestamp":1790340341399,"version":"4.1.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"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":[[2021,5,30]]},"DOI":"10.1109\/icra48506.2021.9561842","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"4202-4208","source":"Crossref","is-referenced-by-count":15,"title":["Sample Efficient Reinforcement Learning via Model-Ensemble Exploration and Exploitation"],"prefix":"10.1109","author":[{"given":"Yao","family":"Yao","sequence":"first","affiliation":[{"name":"Tsinghua University,TBSI, Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Xiao","sequence":"additional","affiliation":[{"name":"Tsinghua University,TBSI, Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhicheng","family":"An","sequence":"additional","affiliation":[{"name":"Tsinghua University,TBSI, Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tsinghua University,TBSI, Tsinghua Shenzhen International Graduate School,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dijun","family":"Luo","sequence":"additional","affiliation":[{"name":"Tencent AI Lab,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Model-based value estimation for efficient model-free reinforcement learning","author":"feinberg","year":"2018"},{"key":"ref38","first-page":"1109","article-title":"Vime: Variational information maximizing exploration","author":"houthooft","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"222","DOI":"10.7551\/mitpress\/3115.003.0030","article-title":"A possibility for implementing curiosity and boredom in model-building neural controllers","author":"schmidhuber","year":"1991","journal-title":"Proc of the International Conference on Simulation of Adaptive Behavior From Animals to Animats"},{"key":"ref32","first-page":"34","article-title":"Improving pilco with bayesian neural network dynamics models","volume":"4","author":"gal","year":"2016","journal-title":"Data-Efficient Machine Learning workshop"},{"key":"ref31","first-page":"6166","article-title":"Model predictive control using neural networks","volume":"15","author":"draeger","year":"1995","journal-title":"IEEE Control Systems Magazine"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487156"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref36","article-title":"Incentivizing exploration in reinforcement learning with deep predictive models","author":"stadie","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2006.890271"},{"key":"ref34","article-title":"Exploration strategies in deep reinforcement learning","author":"weng","year":"2020","journal-title":"lilianweng github io\/lil-log"},{"key":"ref10","first-page":"4754","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref40","first-page":"8224","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","author":"buckman","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref11","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","author":"janner","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Self-supervised exploration via disagreement","author":"pathak","year":"2019"},{"key":"ref13","article-title":"Combating the compounding-error problem with a multi-step model","author":"asadi","year":"2019"},{"key":"ref14","article-title":"Sde-net: Equipping deep neural networks with uncertainty estimates","author":"kong","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref16","first-page":"5779","article-title":"Model-based active exploration","author":"shyam","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref18","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref28","doi-asserted-by":"crossref","DOI":"10.1109\/TRO.2020.2988642","article-title":"Tossing-bot: Learning to throw arbitrary objects with residual physics","author":"zeng","year":"2020","journal-title":"IEEE Transactions on Robotics"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref27","article-title":"Learning to perform physics experiments via deep reinforcement learning","author":"denil","year":"2016"},{"key":"ref3","article-title":"Agent57: Outperforming the atari human benchmark","author":"badia","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2958211"},{"key":"ref29","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"key":"ref5","article-title":"Rlcard: A toolkit for reinforcement learning in card games","author":"zha","year":"2019"},{"key":"ref8","article-title":"Model-based reinforcement learning for atari","author":"kaiser","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref9","article-title":"Model-ensemble trust-region policy optimization","author":"kurutach","year":"2018"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref46","article-title":"Sunrise: A simple unified framework for ensemble learning in deep reinforcement learning","author":"lee","year":"2020"},{"key":"ref20","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018"},{"key":"ref45","article-title":"Planning to explore via self-supervised world models","author":"sekar","year":"2020"},{"key":"ref22","first-page":"652","article-title":"Doubly robust off-policy value evaluation for reinforcement learning","author":"jiang","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref21","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref42","first-page":"2575","article-title":"Variational dropout and the local reparameterization trick","author":"kingma","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/978-3-642-27645-3_2","article-title":"Batch reinforcement learning","author":"lange","year":"2012","journal-title":"Reinforcement Learning"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref23","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref44","article-title":"Large-scale study of curiosity-driven learning","author":"burda","year":"2018"},{"key":"ref26","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"garca","year":"2015","journal-title":"Journal of Machine Learning Research"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.009"},{"key":"ref25","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2019","journal-title":"International Conference on Machine Learning"}],"event":{"name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","location":"Xi'an, China","start":{"date-parts":[[2021,5,30]]},"end":{"date-parts":[[2021,6,5]]}},"container-title":["2021 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9560720\/9560666\/09561842.pdf?arnumber=9561842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T06:17:07Z","timestamp":1725949027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9561842\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9561842","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}