We investigate whether Deep Reinforcement Learning (Deep RL) is able to
...
Despite recent progress in reinforcement learning (RL), RL algorithms fo...
Many advances that have improved the robustness and efficiency of deep
r...
Many real-world problems require trading off multiple competing objectiv...
Robots can learn preferences from human demonstrations, but their succes...
Robots must know how to be gentle when they need to interact with fragil...
People frequently face challenging decision-making problems in which out...
In order to effectively interact with or supervise a robot, humans need ...
Our goal is to enable robots to express their incapability, and to do so...