My PhD project focuses on techniques for safe reinforcement learning. More generally, I’m interested in the problem of AI alignment – how we can create artificial agents that act in accordance with our values, even if those values are somewhat messy.
I was interested in joining the CDT for two reasons. Firstly, the cohort structure means there’s more community than in a traditional PhD, which makes the whole process more enjoyable. Secondly, that community is centred around the subfield I’m interested in – and that comes with opportunities for collaboration and mentorship that will help make me a better researcher.
Undergraduate Qualification: MSci Mathematics, University of Bristol
Work Experience: I enjoy teaching. During my time in Bristol, I ran a Maths Café in number theory, and so far at Imperial I’ve helped out with an introductory course in symbolic AI.