Research Scientist at DeepMind
My main interest is in understanding deep learning systems, especially reinforcement learning agents. I’m particularly interested in what we can learn from very capable agents, how they learn, and whether they represent their domain in ways we understand. I’m also interested in applications of interpretability to science and safety.
I did my PhD (thesis) at Imperial College with Nick Jones and Kevin Murphy.
My papers are listed on my Google Scholar page.
Email is probably best, but you can reach me on Twitter or LinkedIn as well.