Biography
I am a 4th year Doctoral Candidate in the FLAIR and WHIRL labs at the University of Oxford. I am also a member of the AIMS CDT. I am interested in properly evaluating and understanding the training of agents, mostly using reinforcement learning.
I previously worked as a software engineer for Man AHL for two years, where I worked in the Core Trading Technology team. Before that I did my masters and undergraduate degrees in computer science at the University of Cambridge.
Interests
- Reinforcement Learning
- Multi-Agent Reinforcement Learning
Education
DPhil in Machine Learning, 2020-2024
University of Oxford
MEng in Computer Science, 2018
University of Cambridge
BA in Computer Science, 2018
University of Cambridge
Recent Publications
(2024).
Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning.
arXiv preprint arXiv:2402.16801.
(2024).
Smacv2: An improved benchmark for cooperative multi-agent reinforcement learning.
Advances in Neural Information Processing Systems.
(2023).
Jaxmarl: Multi-agent rl environments in jax.
arXiv preprint arXiv:2311.10090.
(2023).
Trust-region-free policy optimization for stochastic policies.
RLDM 2022.
(2022).
Generalization in cooperative multi-agent systems.
arXiv preprint arXiv:2202.00104.