My primary research interests focus on the core artificial intelligence ambition of creating artifical autonomous agents that can behave flexibly and competently in rich, complex environments. I tend to approach this problem through my background in machine learning, and specifically reinforcement learning. Broadly speaking, then, I focus on the learning problem faced by an agent that is placed in an unknown environment and would like to learn, from its own experience, how to make good decisions (where "good" is defined by some specified reward signal). This raises interesting and challenging questions about how such an agent should represent and maintain knowledge in order to make both learning and planning tractible, even when the world is very complex. Beyond this primary focus, I am also quite broadly interested in machine learning in general as a tool for turning the ever-growing mountain of available data into useful computational artifacts
