The application of deep learning in robotics leads to very specific problems and research
questions that are typically not addressed by the computer vision and machine learning …

Applying end-to-end learning to solve complex, interactive, pixel-driven control tasks on a
robot is an unsolved problem. Deep Reinforcement Learning algorithms are too slow to …

Machine learning has become an important research area in many domains and real-world
applications. The prevailing assumption in traditional machine learning techniques, that …

Developing control policies in simulation is often more practical and safer than directly
running experiments in the real world. This applies to policies obtained from planning and …

Sim-to-real transfer is a powerful paradigm for robotic reinforcement learning. The ability to
train policies in simulation enables safe exploration and large-scale data collection quickly …

Learning from small data sets is critical in many practical applications where data collection
is time consuming or expensive, eg, robotics, animal experiments or drug design. Meta …

Humans have a remarkable ability to learn new concepts from only a few examples and
quickly adapt to unforeseen circumstances. To do so, they build upon their prior experience …

We introduce a method for constructing skills capable of solving tasks drawn from a
distribution of parameterized reinforcement learning problems. The method draws example …

Learning policies that generalize across multiple tasks is an important and challenging
research topic in reinforcement learning and robotics. Training individual policies for every …

Deep reinforcement learning could be used to learn dexterous robotic policies but it is
challenging to transfer them to new robots with vastly different hardware properties. It is also …