As natural language interfaces enable users to express increasingly comp...
Learning good representations is a long standing problem in reinforcemen...
In distributional reinforcement learning (RL), the estimated distributio...
Learning an effective representation for high-dimensional data is a
chal...
In this paper, we propose the Quantile Option Architecture (QUOTA) for
e...
Online real-estate information systems such as Zillow and Trulia have ga...
In this paper, we study a new type of spatial sparse recovery problem, t...