My academic interests are broad, but in general I am concerned with how agents reason and make inferences about causality and preferences in order to make decisions in the face of uncertainty, and how the formal tools of logic and mathematics can be used to analyse and verify such processes. I am particularly interested by how elements of classical (symbolic) and statistical (sub-symbolic) AI can be combined in order to help ensure that our increasingly ubiquitous and powerful AI technologies are provably robust, explainable, and beneficial. At present, my work focuses on the verification of multi-agent and machine learning systems. Wider topics that my interests overlap with include (in no particular order): machine learning, logic, formal methods, game/decision theory, knowledge representation, probabilistic graphical models, computational social choice, and machine ethics.
I am supervised by Michael Wooldridge, Julian Gutierrez, and Alessandro Abate, and am also a DPhil Affiliate at the Future of Humanity Institute. Before coming to Oxford I worked as an intern on Imandra and was a research assistant for Jacques Fleuriot at the University of Edinburgh, where I completed my MSc in artificial intelligence under the supervision of Vaishak Belle. Prior to this I studied for my BSc in mathematics and philosophy at the University of Warwick with Walter Dean. I am originally from Shrewsbury in the UK.
- Future of Humanity InstituteDPhil Affiliate
- Logics for strategic reasoning
- Complexity and equilibria
- Quantitative Analysis and Verification
- Rational verification