no code implementations • 16 Jun 2021 • Siyu Dai, Andreas Hofmann, Brian Williams
We propose Automatic Curricula via Expert Demonstrations (ACED), a reinforcement learning (RL) approach that combines the ideas of imitation learning and curriculum learning in order to solve challenging robotic manipulation tasks with sparse reward functions.
no code implementations • 3 Dec 2020 • Siyu Dai, Andreas Hofmann, Brian C. Williams
Many real-world robotic operations that involve high-dimensional humanoid robots require fast-reaction to plan disturbances and probabilistic guarantees over collision risks, whereas most probabilistic motion planning approaches developed for car-like robots can not be directly applied to high-dimensional robots.
no code implementations • 15 Oct 2020 • Siyu Dai, Wei Xu, Andreas Hofmann, Brian Williams
In order to provide adaptive and user-friendly solutions to robotic manipulation, it is important that the agent can learn to accomplish tasks even if they are only provided with very sparse instruction signals.