My research interest lies in a multidisciplinary approach to studying learning, adaptation, and goal-directed behaviour in multi-agent systems. I learn and draw inspiration from a variety of fields such as artificial intelligence, computer science, mathematics, computational neuroscience, cognitive science, and psychology.
My current research is on computational models for incentive design and rational verification in multi-agent systems. The objective is to study methods for top-down influence on the collective behaviour of multi-agent systems.
I am supervised by Michael Wooldridge and Julian Gutierrez. Prior to Oxford, I studied at the University of Sydney and undertook several research projects as an undergraduate. I completed a summer research scholarship and research assistantship with Vincent Gramoli and Gauthier Voron working on performance benchmarking for the DBFT consensus algorithm on the Corda blockchain. Following this, I initiated a TSP project with Peter Kim studying, implementing, and visualising 2D agent-based models of immune cell interactions in C++. Before my honours year, I did a summer research internship in bioinformatics at The Kinghorn Cancer Centre where I implemented an automated general hyperparameter optimisation method based on binary search and wrote a parallelised implementation of a Nanopore DNA analysis algorithm using SIMD. During my honours year, I studied and implemented an entropy-regularised continuous time Reinforcement Learning algorithm under the supervision of Zhou Zhou.