{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T13:39:25Z","timestamp":1769521165117,"version":"3.49.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1109\/iros.2018.8594341","type":"proceedings-article","created":{"date-parts":[[2019,1,24]],"date-time":"2019-01-24T02:33:30Z","timestamp":1548297210000},"page":"4115-4122","source":"Crossref","is-referenced-by-count":5,"title":["Improving Reinforcement Learning Pre-Training with Variational Dropout"],"prefix":"10.1109","author":[{"given":"Tom","family":"Blau","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lionel","family":"Ott","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Ramos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref11","article-title":"Concrete dropout","author":"gal","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref12","author":"geoffrey","year":"2012","journal-title":"Improving Neural Networks by Preventing Co-adaptation of Feature Detectors"},{"key":"ref13","article-title":"Generative adversarial imitation learning","author":"ho","year":"2016","journal-title":"NIPS"},{"key":"ref14","author":"kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref15","article-title":"Dart: Noise injection for robust imitation learning","author":"laskey","year":"2017","journal-title":"Conference on Robot Learning"},{"key":"ref16","article-title":"Learning hand-eye coordination for robotic grasping with deep learning and large-scale data collection","author":"levine","year":"2016","journal-title":"ArXiv e-prints"},{"key":"ref17","article-title":"Human-level control through deep reinforcement learning","author":"volodymyr","year":"2015","journal-title":"Nature"},{"key":"ref18","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref19","article-title":"Variational dropout sparsifies deep neural networks","author":"molchanov","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref4","author":"bojarski","year":"2016","journal-title":"End to End Learning for Self-Driving Cars"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref6","author":"dieleman","year":"2015","journal-title":"Lasagne First Release"},{"key":"ref5","author":"bojarski","year":"2016","journal-title":"End to End Learning for Self-Driving Cars"},{"key":"ref8","article-title":"One-shot imitation learning","author":"duan","year":"2017","journal-title":"NIPS"},{"key":"ref7","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref2","article-title":"Adaptive dropout for training deep neural networks","author":"ba","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref9","article-title":"V-rep: a versatile and scalable robot simulation framework","author":"freese","year":"2013","journal-title":"Proc of the International Conference on Intelligent Robots and Systems"},{"key":"ref1","author":"achille","year":"2016","journal-title":"Information dropout learning optimal representations through noise"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.88"},{"key":"ref22","author":"rusu","year":"2015","journal-title":"Policy distillation"},{"key":"ref21","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","author":"ross","year":"2011","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"ref24","author":"srinivas","year":"2016","journal-title":"Generalized dropout"},{"key":"ref23","article-title":"Trust region policy optimization","author":"john","year":"2015","journal-title":"International Conference on Machine Learning"},{"key":"ref26","author":"wymann","year":"2014","journal-title":"TORCS The Open Racing Car Simulator"},{"key":"ref25","article-title":"Dropout: A simple way to prevent neural networks from overfitting","author":"srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"}],"event":{"name":"2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Madrid","start":{"date-parts":[[2018,10,1]]},"end":{"date-parts":[[2018,10,5]]}},"container-title":["2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8574473\/8593358\/08594341.pdf?arnumber=8594341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T05:49:29Z","timestamp":1598248169000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8594341\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,10]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/iros.2018.8594341","relation":{},"subject":[],"published":{"date-parts":[[2018,10]]}}}