Learning-based methods in robotics hold the promise of generalization, b...
The utilization of broad datasets has proven to be crucial for generaliz...
General-purpose robots require diverse repertoires of behaviors to compl...
Building generalizable goal-conditioned agents from rich observations is...
Offline reinforcement learning requires reconciling two conflicting aims...
Meta-reinforcement learning (RL) can meta-train policies that adapt to n...
A generalist robot equipped with learned skills must be able to perform ...
Can we use reinforcement learning to learn general-purpose policies that...
Reinforcement learning provides an appealing formalism for learning cont...
Robotic insertion tasks are characterized by contact and friction mechan...
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 ...
Exploration in environments with sparse rewards has been a persistent pr...
Manipulation of deformable objects, such as ropes and cloth, is an impor...
We investigate an experiential learning paradigm for acquiring an intern...