{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T11:57:15Z","timestamp":1746187035003,"version":"3.28.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,10,24]],"date-time":"2020-10-24T00:00:00Z","timestamp":1603497600000},"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":[[2020,10,24]]},"DOI":"10.1109\/iros45743.2020.9340873","type":"proceedings-article","created":{"date-parts":[[2021,3,15]],"date-time":"2021-03-15T14:49:56Z","timestamp":1615819796000},"page":"5611-5618","source":"Crossref","is-referenced-by-count":24,"title":["PlaNet of the Bayesians: Reconsidering and Improving Deep Planning Network by Incorporating Bayesian Inference"],"prefix":"10.1109","author":[{"given":"Masashi","family":"Okada","sequence":"first","affiliation":[{"name":"Panasonic Corporation,AI Solutions Center, Business Innovation Division,Japan"}]},{"given":"Norio","family":"Kosaka","sequence":"additional","affiliation":[{"name":"Panasonic Corporation,AI Solutions Center, Business Innovation Division,Japan"}]},{"given":"Tadahiro","family":"Taniguchi","sequence":"additional","affiliation":[{"name":"Panasonic Corporation,AI Solutions Center, Business Innovation Division,Japan"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Disentangling controllable and uncontrollable factors of variation by interacting with the world","author":"sawada","year":"2018","journal-title":"NeurIPS Workshop on Deep Reinforcement Learning"},{"key":"ref38","article-title":"Disentangling the independently controllable factors of variation by interacting with the world","author":"thomas","year":"2018","journal-title":"NeurIPS Learning Disentangling Representations Workshop"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1109\/IROS45743.2020.9341705","article-title":"Domain-adversarial and-conditional state space model for imitation learning","author":"okumura","year":"2020"},{"article-title":"Model-based reinforcement learning for atari","year":"2019","author":"kaiser","key":"ref32"},{"key":"ref31","article-title":"Variational recurrent models for solving partially observable control tasks","author":"han","year":"2020","journal-title":"International Conference on Learning Representations (ICLR)"},{"article-title":"Deep variational reinforcement learning for POMDPs","year":"2018","author":"igl","key":"ref30"},{"article-title":"Mastering Atari, go, chess and shogi by planning with a learned model","year":"2019","author":"schrittwieser","key":"ref37"},{"key":"ref36","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":"ref35","article-title":"Bayesian layers: A module for neural network uncertainty","author":"tran","year":"2019","journal-title":"Neural Information Processing Systems"},{"key":"ref34","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref10","article-title":"Model-ensemble trust-region policy optimization","author":"kurutach","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00976"},{"key":"ref11","article-title":"Model-based reinforcement learning via meta-policy optimization","author":"clavera","year":"2018","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref12","article-title":"Variational inference MPC for bayesian model-based reinforcement learning","author":"okada","year":"2019","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref13","article-title":"Deep dynamics models for learning dexterous manipulation","author":"nagabandi","year":"2019","journal-title":"Conference on Robot Learning (CoRL)"},{"article-title":"Reinforcement learning and control as probabilistic inference: Tutorial and review","year":"2018","author":"levine","key":"ref14"},{"key":"ref15","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/B978-0-444-53859-8.00003-5","article-title":"The cross-entropy method for optimization","volume":"31","author":"botev","year":"2013","journal-title":"Handbook of Statistics"},{"article-title":"DeepMind control suite","year":"2018","author":"tassa","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"article-title":"Path integral networks: End-to-end differentiable optimal control","year":"2017","author":"okada","key":"ref19"},{"article-title":"World models","year":"2018","author":"ha","key":"ref28"},{"key":"ref4","article-title":"Learning latent dynamics for planning from pixels","author":"hafner","year":"2019","journal-title":"International Conference on Machine Learning (ICML)"},{"article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","year":"2015","author":"abadi","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MIE.2013.2290138"},{"key":"ref6","article-title":"Dropout as a bayesian approximation: Representing model uncertainty in deep learning","author":"gal","year":"2016","journal-title":"International Conference on Machine Learning (ICML)"},{"article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","year":"2019","author":"lee","key":"ref29"},{"key":"ref5","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"International Conference on Machine Learning (ICML)"},{"article-title":"Uncertainty- aware reinforcement learning for collision avoidance","year":"2017","author":"kahn","key":"ref8"},{"key":"ref7","article-title":"Concrete dropout","author":"gal","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0098-1354(00)00598-6"},{"key":"ref9","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"chua","year":"2018","journal-title":"Neural Information Processing Systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2013.11.016"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487277"},{"key":"ref22","article-title":"The cross-entropy method optimizes for quantiles","author":"goschin","year":"2013","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/106365603321828970"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1561\/9781601988614"},{"article-title":"Bayesian variational autoencoders for unsupervised out-of-distribution detection","year":"2019","author":"daxberger","key":"ref23"},{"key":"ref26","first-page":"52","volume":"45","author":"thrun","year":"2002","journal-title":"Probabilistic Robotics"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463164"}],"event":{"name":"2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2020,10,24]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2021,1,24]]}},"container-title":["2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9340668\/9340635\/09340873.pdf?arnumber=9340873","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,28]],"date-time":"2022-06-28T21:51:55Z","timestamp":1656453115000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9340873\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,24]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iros45743.2020.9340873","relation":{},"subject":[],"published":{"date-parts":[[2020,10,24]]}}}