Leveraging Structure to Efficiently Make Good Decisions in an Uncertain World

***Refreshments at 11:50am***

Abstract:

Making good sequential decisions under uncertainty is a core part of what it means to be smart. It is formally hard to solve these problems when part of the environment is hidden, and most such real problems are intractable to solve with general-purpose algorithms. Developing approaches that scale to much larger, more complex domains could lead to profound impact on applications ranging from patient treatment to mobile manipulation to computer assisted education.

In this talk I will discuss several algorithms that leverage structure common in diverse problem classes in order to efficiently make decisions in dramatically larger domains. I will present results on autonomous helicopter surveillance and share results of a field study in Bangalore, India demonstrating that an adaptive tutoring software game has the potential to increase student engagement.