Abstract:  I will discuss a research program aimed at building a Minecraft assistant, in order to facilitate the study of agents that can complete tasks specified by dialogue, and eventually, to learn from dialogue interactions.  I will describe the tools and platform we have built allowing players to interact with the agents and to record those interactions, and the data we have collected.  In addition, I will describe an initial agent from which we (and hopefully others) can iterate.

Bio: Prior to joining Facebook, I was an assistant professor at CCNY in the math department. I did my PhD under R. Coifman at Yale.  My interests are in machine learning, harmonic analysis on graphs, and data.

Homepage: https://research.fb.com/people/szlam-arthur/