A robot's ability to act is fundamentally constrained by what it can
per...
Model-free reinforcement learning algorithms such as Deep Deterministic
...
We present a framework for data-driven robotics that makes use of a larg...
We propose Generative Predecessor Models for Imitation Learning (GPRIL),...
We propose a general and model-free approach for Reinforcement Learning ...
We propose position-velocity encoders (PVEs) which learn---without
super...