no code implementations • 30 Sep 2020 • Mel Vecerik, Jean-Baptiste Regli, Oleg Sushkov, David Barker, Rugile Pevceviciute, Thomas Rothörl, Christopher Schuster, Raia Hadsell, Lourdes Agapito, Jonathan Scholz
In this work we advocate semantic 3D keypoints as a visual representation, and present a semi-supervised training objective that can allow instance or category-level keypoints to be trained to 1-5 millimeter-accuracy with minimal supervision.
Insertion is a challenging haptic and visual control problem with significant practical value for manufacturing.
We show that models trained to predict proprioceptive information about the agent's body come to represent objects in the external world.
We propose a general and model-free approach for Reinforcement Learning (RL) on real robotics with sparse rewards.
The progressive net approach is a general framework that enables reuse of everything from low-level visual features to high-level policies for transfer to new tasks, enabling a compositional, yet simple, approach to building complex skills.