My research involves the behavioural regulation of reinforcement learning agents such that these agents are better able to integrate with the societies in which they operate.
My research also looks to develop interpretable methods such that policy makers and regulators are better able to trust the AI systems they regulate.
My interests include Multi-Agent Reinforcement Learning, Normative Reasoning, Neural Networks, Neuro-Symbolic AI and AI Fairness.
I chose to do a PhD through the STAI CDT because it offered a cohort-based model that focuses on collaboration with like-minded students and because I was interested in developing AI systems that emphasised putting the wellbeing of society over all else.
Undergraduate Qualification: BSc Games Programming, Goldsmiths, University of London
Masters Qualification: MSc Artificial Intelligence, King’s College London