We present a novel approach to address the challenge of generalization i...
Language Models and Vision Language Models have recently demonstrated
un...
We investigate the use of transformer sequence models as dynamics models...
We investigate whether Deep Reinforcement Learning (Deep RL) is able to
...
In this paper we study the problem of learning multi-step dynamics predi...
We present a system for applying sim2real approaches to "in the wild" sc...
Actor-critic algorithms that make use of distributional policy evaluatio...
Offline Reinforcement Learning (ORL) enablesus to separately study the t...
We study the problem of robotic stacking with objects of complex geometr...
There is a widespread intuition that model-based control methods should ...
Model-Based Reinforcement Learning involves learning a dynamics
model fr...
Many advances that have improved the robustness and efficiency of deep
r...
Projecting high-dimensional environment observations into lower-dimensio...
We present an algorithm for local, regularized, policy improvement in
re...
In this work, we bridge the gap between recent pose estimation and track...
Humans are masters at quickly learning many complex tasks, relying on an...
High-level human instructions often correspond to behaviors with multipl...
In this work, we present an approach to deep visuomotor control using
st...
We introduce SE3-Nets, which are deep neural networks designed to model ...