I am a Computer Science PhD candidate working on reinforcement learning, and am advised by George Konidaris in the Intelligent Robot Lab at Brown University. Solving a task with RL takes a blend of data-gathering and curve-fitting, and I work on both parts of this problem. My primary interest is developing better exploration methods, which can direct the agent towards data that makes the most learning progress. I also work on improving the parts of the RL optimization problem that make it different from standard supervised learning, such as bootstrapping and action selection. My work is funded in part by the NSF Graduate Research Fellowship.
I graduated from the University of Pennsylvania in 2015, where I studied Physics, Math, and a little bit of Computer Science. Between then and graduate school I held a variety of jobs as a programmer while also gearing up for my current post.