The choice of a grasp plays a critical role in the success of downstream...
In a Human-in-the-Loop paradigm, a robotic agent is able to act mostly
a...
Controlling robotic manipulators with high-dimensional action spaces for...
We introduce the Universal Manipulation Policy Network (UMPNet) – a sing...
3D scene representation for robot manipulation should capture three key
...
Deep Reinforcement Learning (RL) has shown great success in learning com...
Recent advances in deep reinforcement learning (RL) have demonstrated it...
Meta-reinforcement learning algorithms can enable robots to acquire new
...
Simulation-to-real transfer is an important strategy for making reinforc...
We present a novel solution to the problem of simulation-to-real transfe...