I am a fourth-year computer science PhD student at the University of California, Irvine. My advisor is Pierre Baldi. My research is mainly in deep reinforcement learning and game theory, but I also work on applications of deep learning in the natural sciences. Last year my research led to the first algorithm that can solve the Rubik's Cube with reinforcement learning. I am currently working on using deep reinforcement learning to find approximate Nash equilibria in large games such as Stratego. Last summer I interned at Intel AI in San Diego and I will intern at DeepMind in 2021. I received a bachelor's degree in mathematics and economics from Arizona State University in 2017.

Google Scholar