MrAlex Goodall

I am a PhD candidate working in safe Reinforcement Learning (RL) from a formal methods/model checking perspective. More specifically I am looking at leveraging world models for verifying the safety of RL policies with respect to a set of safety constraints given as a temporal logic formula. The goal is to develop a robust and safe RL algorithm with provable guarantees, that can be deployed in the real world.

I come from a Computer Science background with a focus on Artficial Intelligence (AI) and statistical Machine Learning (ML) methods. Prior to Imperial I completed my Bachelor's in Computer Science at Durham University and my Master's in Advanced Computer Science at the University of Oxford.

Outside of my immediate research, my interests lie in RL more broadly, Bayesian ML and Neuroscience inspired AI.