{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:53:44Z","timestamp":1775066024727,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,5,30]],"date-time":"2021-05-30T00:00:00Z","timestamp":1622332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"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\/icra48506.2021.9560734","type":"proceedings-article","created":{"date-parts":[[2021,10,20]],"date-time":"2021-10-20T00:28:35Z","timestamp":1634689715000},"page":"4209-4215","source":"Crossref","is-referenced-by-count":36,"title":["Dreaming: Model-based Reinforcement Learning by Latent Imagination without Reconstruction"],"prefix":"10.1109","author":[{"given":"Masashi","family":"Okada","sequence":"first","affiliation":[]},{"given":"Tadahiro","family":"Taniguchi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","author":"Chua","year":"2018","journal-title":"NeurIPS"},{"key":"ref2","article-title":"Variational inference MPC for Bayesian model-based reinforcement learning","author":"Okada","year":"2019","journal-title":"CoRL"},{"key":"ref3","article-title":"Benchmarking model-based reinforcement learning","author":"Langlois","year":"2019"},{"key":"ref4","article-title":"Model-based reinforcement learning for Atari","author":"Kaiser","year":"2020","journal-title":"ICLR"},{"key":"ref5","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018","journal-title":"ICML"},{"key":"ref6","article-title":"Curious iLQR: Resolving uncertainty in model-based RL","author":"Bechtle","year":"2019","journal-title":"CoRL"},{"key":"ref7","article-title":"Deep dynamics models for learning dexterous manipulation","author":"Nagabandi","year":"2019","journal-title":"CoRL"},{"key":"ref8","article-title":"Data efficient reinforcement learning for legged robots","author":"Yang","year":"2019","journal-title":"CoRL"},{"key":"ref9","article-title":"Asynchronous methods for model-based reinforcement learning","author":"Zhang","year":"2019","journal-title":"CoRL"},{"key":"ref10","article-title":"Locally weighted regression pseudo-rehearsal for adaptive model predictive control","author":"Williams","year":"2019","journal-title":"CoRL"},{"key":"ref11","article-title":"Dynamics learning with cascaded variational inference for multi-step manipulation","author":"Fang","year":"2019","journal-title":"CoRL"},{"key":"ref12","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"ICLR"},{"key":"ref13","article-title":"Recurrent world models facilitate policy evolution","author":"Ha","year":"2018","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model","author":"Lee","year":"2019"},{"key":"ref15","article-title":"Learning latent dynamics for planning from pixels","author":"Hafner","year":"2019","journal-title":"ICML"},{"key":"ref16","article-title":"Dream to control: Learning behaviors by latent imagination","author":"Hafner","year":"2020","journal-title":"ICLR"},{"key":"ref17","article-title":"Variational recurrent models for solving partially observable control tasks","author":"Han","year":"2020","journal-title":"ICLR"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340873"},{"key":"ref20","article-title":"DeepMind control suite","author":"Tassa","year":"2018"},{"key":"ref21","article-title":"Learning predictive representations for deformable objects using contrastive estimation","author":"Yan","year":"2020"},{"key":"ref22","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref23","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020","journal-title":"ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref25","article-title":"CURL: Contrastive unsupervised representations for reinforcement learning","author":"Srinivas","year":"2020","journal-title":"ICML"},{"key":"ref26","article-title":"Learning invariant representations for reinforcement learning without reconstruction","author":"Zhang","year":"2020"},{"key":"ref27","article-title":"Discriminative particle filter reinforcement learning for complex partial observations","author":"Ma","year":"2020","journal-title":"ICLR"},{"key":"ref28","article-title":"Reinforcement learning with augmented data","author":"Laskin","year":"2020"},{"key":"ref29","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","author":"Kostrikov","year":"2020"},{"key":"ref30","article-title":"SUNRISE: A simple unified framework for ensemble learning in deep reinforcement learning","author":"Lee","year":"2020"},{"key":"ref31","article-title":"Planning to explore via self-supervised world models","author":"Sekar","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref33","article-title":"On variational bounds of mutual information","author":"Poole","year":"2019","journal-title":"ICML"},{"key":"ref34","article-title":"On mutual information maximization for representation learning","author":"Tschannen","year":"2020","journal-title":"ICLR"},{"key":"ref35","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2015"},{"key":"ref36","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"Deisenroth","year":"2011","journal-title":"ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341705"}],"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\/09560734.pdf?arnumber=9560734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:43:56Z","timestamp":1706060636000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9560734\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,30]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icra48506.2021.9560734","relation":{},"subject":[],"published":{"date-parts":[[2021,5,30]]}}}