The ability to leverage heterogeneous robotic experience from different
...
The ability to effectively reuse prior knowledge is a key requirement wh...
Reinforcement learning (RL) has been shown to be effective at learning
c...
We study the problem of robotic stacking with objects of complex geometr...
Projecting high-dimensional environment observations into lower-dimensio...
Robot manipulation requires a complex set of skills that need to be care...
Solutions to most complex tasks can be decomposed into simpler, intermed...
Off-policy reinforcement learning algorithms promise to be applicable in...
Many real-world control problems involve both discrete decision variable...
Learning robotic control policies in the real world gives rise to challe...
Collecting and automatically obtaining reward signals from real robotic
...
Humans are masters at quickly learning many complex tasks, relying on an...
The successful application of flexible, general learning algorithms -- s...
We present a method for fast training of vision based control policies o...
We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm ...
We propose a general and model-free approach for Reinforcement Learning ...