We develop information-geometric techniques to analyze the trajectories ...
We develop a technique to analyze representations learned by deep networ...
More data helps us generalize to a task. But real datasets can contain
o...
What is the best way to exploit extra data – be it unlabeled data from t...
Leveraging data from multiple tasks, either all at once, or incrementall...
Option discovery and skill acquisition frameworks are integral to the
fu...
The options framework in reinforcement learning models the notion of a s...
Deep Learning has managed to push boundaries in a wide variety of tasks....
We consider the problem of computing a matching in a bipartite graph in ...
Deep Reinforcement Learning (DRL) methods have performed well in an
incr...