Experimentation on real robots is demanding in terms of time and costs. ...
Learning policies from previously recorded data is a promising direction...
Robotic applications require the integration of various modalities,
enco...
This paper describes a deep reinforcement learning (DRL) approach that w...
We present a system for learning a challenging dexterous manipulation ta...
Learning data representations that are useful for various downstream tas...
Dexterous object manipulation remains an open problem in robotics, despi...
We present a new open-source torque-controlled legged robot system, with...