My project focuses on advancing the concept of Reward Machines (RMs) in reinforcement learning. In particular, I aim to design algorithms to learn RMs in a noisy setting and apply them in real-world scenarios. Reward Machines are inherently interpretable, which helps increase the trust of RL agents using them.
My current research interests span the fields of reinforcement learning, neuro-symbolic learning, machine learning, and robotics. Safe and Trusted AI CDT is a great place to do so. I chose it as I wanted to work within the field of AI safety. It contains a lot of challenging but crucial problems to address. Also, the CDT is cohort-based which helps me learn, meet and collaborate with like-minded peers.
–
Masters Qualification: MEng Computing (Artificial Intelligence)
Work Experience:
- Software Engineer, Meta
- Software Engineer Intern, Microsoft
- Software Engineer Intern, Bloomberg
