Correct Me If I am Wrong: Interactive Learning for Robotic Manipulation

If I am free, you can't own me: Autonomy makes entities less ownable.

Although people own myriad objects, land, and even ideas, it is currently illegal to own other humans. This reluctance to view people as property raises interesting questions about our conceptions of people and about our conceptions of ownership. We suggest that one factor contributing to this reluctance is that humans are normally considered to be autonomous, and autonomy is incompatible with ...

Embodied Inference : or “ I think therefore I am , if I am what I think ”

Interactive Data Mining Considered Harmful (If Done Wrong)

Interactive data mining can be a powerful tool for data analysis. But in this short opinion piece I argue that this power comes with new pitfalls that can undermine the value of interactive mining, if not properly addressed. Most notably, there is a serious risk that the user of powerful interactive data mining tools will only find the results she was expecting. The purpose of this piece is to ...

Composable Deep Reinforcement Learning for Robotic Manipulation

Model-free deep reinforcement learning has been shown to exhibit good performance in domains ranging from video games to simulated robotic manipulation and locomotion. However, model-free methods are known to perform poorly when the interaction time with the environment is limited, as is the case for most real-world robotic tasks. In this paper, we study how maximum entropy policies trained usi...

Deep Reinforcement Learning for Robotic Manipulation

Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of the learning process in favor of achieving training times that are practical for real physical systems. This typically involves introducing hand-engineered ...