Anya Sims

Hi! I’m a second year PhD student at Oxford, supervised by Prof. Yee Whye Teh and part of the StatML CDT and OXCSML group.

I’m currently working on deep reinforcement learning - trying to improve understanding of when and why training fails, and how we can make current algorithms more robust, particularly in offline RL. I’m also exited about using meta-learning to discover reinforcement learning algorithms. More broadly I’m interested in probabilistic machine learning and understanding optimization dynamics in training deep models so that we can make sense of what models are learning and why.

Before coming to Oxford, I completed an integrated Masters in Computer and Information Engineering at the University of Cambridge, where I did my dissertation on language models for automatic speech recognition supervised by Prof. Phil Woodland. I also worked with Prof. José Miguel Hernández-Lobato in the Cambridge Machine Learning Group (MLG) on causal representation learning.