Hi! I’m Tom, a third-year PhD student in the department of Engineering Mathematics at the University Bristol, supervised by Jonathan Lawry and Arthur Richards, supported by Thales, and currently undertaking a year-long Enrichment placement at the Alan Turing Institute. My PhD research in the area of Explainable AI for Autonomous Agents. I’m also a graduate of the UK’s top-ranked general engineering degree, holder of an MSc in Machine Learning, and a recipient of an RAEng Engineering Leaders Scholarship.
My research explores how we might begin to understand and explain the policies of black box autonomous agents, whose internal mechanisms and representations may be very different from our own, with a particular view to revealing the biases and flaws in their decision-making. Critical to this question are the putative trade-off between comprehensibility and performance of machine learning models, and the thorny relationship between correlation and causation in observed data whose generative origins are unknown. I’m increasingly focusing on reinforcement learning agents as the targets of my analysis, with a particular emphasis on building abstract representations of the dynamics of policy evolution during the learning process.
You can find all my proper publications in the 📃 Publications tab, but I’m also exploring using a super-open 🗂️ Research Repo to publicly catalogue my research journey. I’m not quite sure how this little experiment will pan out, but head over there if you’re intrigued.