Offline reinforcement learning (RL) holds promise as a means to learn
hi...
Adaptive interfaces can help users perform sequential decision-making ta...
In this paper, we review the question of which action space is best suit...
This work aims to push the limits of agility for bipedal robots by enabl...
We address the problem of enabling quadrupedal robots to perform precise...
The prototypical approach to reinforcement learning involves training
po...
We aim to help users communicate their intent to machines using flexible...
Building assistive interfaces for controlling robots through arbitrary,
...
We develop a new continual meta-learning method to address challenges in...
Humans and animals explore their environment and acquire useful skills e...
We study how robots can autonomously learn skills that require a combina...
Reinforcement learning (RL) provides a framework for learning goal-direc...
Can we use reinforcement learning to learn general-purpose policies that...
Developing robust walking controllers for bipedal robots is a challengin...
Much of the current work on reinforcement learning studies episodic sett...
Existing approaches for visuomotor robotic control typically require
cha...
All living organisms struggle against the forces of nature to carve out
...
While reinforcement learning provides an appealing formalism for learnin...
People solve the difficult problem of understanding the salient features...
We provide 89 challenging simulation environments that range in difficul...
Bipedal locomotion skills are challenging to develop. Control strategies...
Deep reinforcement learning has demonstrated increasing capabilities for...
The design of a building requires an architect to balance a wide range o...
Deep reinforcement learning has great stride in solving challenging moti...