339 citations · 1.2k across the 31 of their papers we have counts for
6 papers · 1 filter
Evaluating Long-Term Memory in 3D Mazes
Jurgis Pasukonis, Timothy Lillicrap, Danijar Hafner
Intelligent agents need to remember salient information to reason in partially-observed environments. For example, agents with a first-person view should remember the positions of…
Learning Robust Dynamics through Variational Sparse Gating
Arnav Kumar Jain, Shivakanth Sujit, Shruti Joshi +3
Learning world models from their sensory inputs enables agents to plan for actions by imagining their future outcomes. World models have previously been shown to improve sample-eff…
Temporally Consistent Transformers for Video Generation
Wilson Yan, Danijar Hafner, Stephen James +1
To generate accurate videos, algorithms have to understand the spatial and temporal dependencies in the world. Current algorithms enable accurate predictions over short horizons bu…
DayDreamer: World Models for Physical Robot Learning
Philipp Wu, Alejandro Escontrela, Danijar Hafner +2
To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of tria…
Deep Hierarchical Planning from Pixels
Danijar Hafner, Kuang-Huei Lee, Ian Fischer +1
Intelligent agents need to select long sequences of actions to solve complex tasks. While humans easily break down tasks into subgoals and reach them through millions of muscle com…
Masked World Models for Visual Control
Younggyo Seo, Danijar Hafner, Hao Liu +4
Visual model-based reinforcement learning (RL) has the potential to enable sample-efficient robot learning from visual observations. Yet the current approaches typically train a si…