Vision-based tactile sensors typically utilize a deformable elastomer an...
The ability to estimate the 3D human shape and pose from images can be u...
Safety and robustness are two desired properties for any reinforcement
l...
Imitation learning seeks to circumvent the difficulty in designing prope...
Humans quickly solve tasks in novel systems with complex dynamics, witho...
In this paper, we focus on the problem of robustifying reinforcement lea...
Learning to solve complex goal-oriented tasks with sparse terminal-only
...
Deep Reinforcement Learning has shown tremendous success in solving seve...
Learning robot tasks or controllers using deep reinforcement learning ha...