I’m currently a research scientist at OpenAI working on AI safety. I recently graduated with my PhD from UC Berkeley, advised by Pieter Abbeel and Shankar Sastry. My dissertation on “Exploration and Safety in Deep Reinforcment Learning” is available here. I’ve mostly worked on safe exploration in deep RL, but I’m interested in a wide range of topics, including alignment, optimization, ethics, and systems safety. I did my undergraduate studies at University of Florida (go Gators!), where I earned Bachelor of Science degrees in Physics and Aerospace Engineering.

My goals are to ensure that the long-term future of humanity is good and that faster-than-light space travel becomes real.

Other things: I like reading and writing science fiction and fantasy. I know more about Stargate SG1 than is really reasonable for someone to know. Pacific Rim is the greatest movie of all time.