Agents that are aware of the separation between themselves and their
env...
We tackle the problem of learning complex, general behaviors directly in...
Building a robot that can understand and learn to interact by watching h...
Robotic agents that operate autonomously in the real world need to
conti...
To build general robotic agents that can operate in many environments, i...
While reinforcement learning provides an appealing formalism for learnin...
Connector insertion and many other tasks commonly found in modern
manufa...
In standard reinforcement learning, each new skill requires a
manually-d...
Conventional feedback control methods can solve various types of robot
c...
For an autonomous agent to fulfill a wide range of user-specified goals ...