I am a first-year PhD student at the Mathematics Mathematics for Real-World Systems Centre for Doctoral Training (Mathsys II CDT). I am working under the supervision of Prof. Paolo Turrini and Prof. Ann Nowe. My research interests lie in the areas of Machine Learning, Deep Learning and Multi-Objective Reinforcement Learning.

PhD Project: Multi-objective Reinforcement Learning and Fairness

In standard Reinforcement learning the aim is to construct an agent that is able to learn a policy that maximizes a scalar reward signal. However, in many real-world scenarios problems are complicated and they often require a trade-off between multiple and often conflicting objectives. The area of Multi-objective Reinforcement Learning (MORL) aims to tackle this exact issue. My research aims to construct a framework and build algorithms that are able to learn optimal policies in MORL settings. Additionally, this research gives a particular focus on how to incorporate fairness in learning with multiple objectives.