
1
presentations
SHORT BIO
Homepage: https://jparkerholder.github.io/
I am a third-year DPhil student at St Peter's College, Oxford, where I am part of the Machine Learning Research Group, advised by Stephen Roberts.
I am interested in ways to use reinforcement learning (RL) to train generally capable agents. I believe this will be made possible with an open-ended learning process, where environments constantly propose new challenges and agents adapt their configurations to solve them. To make this process unbounded, I am excited by methods to actively encourage diversity, while I believe we can eventually use world models to learn simulators purely from offline data.
Presentations

Lyapunov Exponents for Diversity in Differentiable Games
Jonathan Lorraine and 5 other authors