BACKGROUND Humans have a fantastic ability to manipulate objects of various shapes,
sizes, and materials and can control the objects' position in confined spaces with the …

Deep reinforcement learning has achieved great success in many fields and has shown
promise in learning robust skills for robot control in recent years. However, sampling …

We demonstrate that models trained only in simulation can be used to solve a manipulation
problem of unprecedented complexity on a real robot. This is made possible by two key …

We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies that
can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The …

Achieving human-level dexterity is an important open problem in robotics. However, tasks of
dexterous hand manipulation even at the baby level are challenging to solve through …

Simulations are attractive environments for training agents as they provide an abundant
source of data and alleviate certain safety concerns during the training process. But the …

A wide range of reinforcement learning (RL) problems---including robustness, transfer
learning, unsupervised RL, and emergent complexity---require specifying a distribution of …

We consider the problem of transferring policies to the real world by training on a distribution
of simulated scenarios. Rather than manually tuning the randomization of simulations, we …

Real world data, especially in the domain of robotics, is notoriously costly to collect. One way
to circumvent this can be to leverage the power of simulation to produce large amounts of …

Bridging thereality gap'that separates simulated robotics from experiments on hardware
could accelerate robotic research through improved data availability. This paper explores …