We tackle real-world problems with complex structures beyond the pixel-b...
We study the problem of unsupervised skill discovery, whose goal is to l...
Many real-world problems are compositional - solving them requires compl...
Operating in the real-world often requires agents to learn about a compl...
We propose the k-Shortest-Path (k-SP) constraint: a novel constraint on ...
Learning to reach goal states and learning diverse skills through mutual...
We propose and address a novel few-shot RL problem, where a task is
char...
This paper proposes a method for learning a trajectory-conditioned polic...
This paper investigates whether learning contingency-awareness and
contr...
We propose a novel hierarchical approach for text-to-image synthesis by
...
The attention mechanisms in deep neural networks are inspired by human's...
We propose a high-level concept word detector that can be integrated wit...