Papers of the day   All papers

DREAM TO CONTROL: LEARNING BEHAVIORS BY LATENT IMAGINATION

Comments

Dec 04 2019 Danijar Hafner

We introduce Dreamer, an RL agent that solves long-horizon tasks from images purely by latent imagination inside a world model. Dreamer improves over existing methods across 20 tasks. paper https://arxiv.org/pdf/1912.01603.pdf code https://github.com/google-research/dreamer Thread 👇 https://t.co/K5DnooVIUH
3 replies, 343 likes


Dec 04 2019 hardmaru

Dream to Control: Learning Behaviors by Latent Imagination The agent learns a latent world model via interactions, and backprops thru imagined latent trajectories of this model to learn useful behaviors. @danijarh et al. pdf https://arxiv.org/abs/1912.01603 code https://danijar.com/project/dreamer/ https://t.co/67ePHW3Z2T
4 replies, 190 likes


Dec 04 2019 roadrunner01

Dream to Control: Learning Behaviors by Latent Imagination pdf: https://arxiv.org/pdf/1912.01603.pdf abs: https://arxiv.org/abs/1912.01603 project page: https://danijar.com/project/dreamer/ github: https://github.com/google-research/dreamer videos: https://dreamrl.github.io/ https://t.co/bezVZkB7lE
1 replies, 169 likes


Dec 05 2019 Animesh Garg

Nice work on model learning from @danijarh continuing his line of work on planet Planet ... Dreamer....hmm 😁
1 replies, 13 likes


Dec 04 2019 Shane Gu

Yet another excellent work on visual model-based RL from @danijarh. Excellent results showing how different design choices (e.g. gradient, GAE, contrastive vs reconstruction) lead to changes in performance.
0 replies, 7 likes


Dec 11 2019 Nikolai Rozanov

I had a dream... https://arxiv.org/pdf/1912.01603.pdf Muzero, now dreaming, pretty cool work - thanks for continuing to be original. @danijarh @DeepMindAI
0 replies, 3 likes


Dec 04 2019 Brundage Bot

Dream to Control: Learning Behaviors by Latent Imagination. Danijar Hafner, Timothy Lillicrap, Jimmy Ba, and Mohammad Norouzi http://arxiv.org/abs/1912.01603
1 replies, 1 likes


Content