Alexander D. Goldie

PhD Student, University of Oxford

I am a PhD student at the University of Oxford, supervised by Jakob Foerster and Shimon Whiteson. My research focuses on (meta-)reinforcement learning, automated algorithm discovery, and autonomous research and discovery.

I'm currently a research intern at Meta on the AI Research Agents team, supervised by Yoram Bachrach. Before that, I was a Research Scientist Intern at Wayve, working on offline reinforcement learning for autonomous driving. My PhD is offered by AIMS, a competitive PhD-level course for Machine Learning.

Alexander D. Goldie

News

Earlier entries
  • Nov 2025My internship at Wayve finished. During my internship, for a while, I developed the main model which was driving the Wayve car!
  • Aug 2025I was invited to talk on two episodes of TalkRL.
  • Aug 2025My paper was awarded “Outstanding Paper for Scientific Understanding In Reinforcement Learning” at RLC 2025!
  • Jun 2025I started a Research Scientist internship at Wayve.
  • Dec 2024OPEN was awarded a Spotlight at NeurIPS 2024!
  • Jul 2024I took part in a panel discussion at the AutoRL workshop in ICML24.
  • Jun 2024OPEN was awarded a Spotlight at the AutoRL workshop in ICML24.
  • Oct 2022I started my PhD on AIMS at the University of Oxford.
  • Jul 2022I graduated from my MEng Engineering Science at the University of Oxford with a high First!

Selected Publications

DiscoGen

DiscoGen: Procedural Generation of Algorithm Discovery Tasks in Machine Learning

Alexander D. Goldie, Zilin Wang, Adrian Hayler, et al.

ICML 2026

talks: Hannover · Cambridge (CaMLSys) · Inherent Labs · AIDDA

How Should We Meta-Learn RL Algorithms

How Should We Meta-Learn Reinforcement Learning Algorithms?

Alexander D. Goldie, Zilin Wang, Jaron Cohen, Jakob N. Foerster, Shimon Whiteson

RLC 2025 · Outstanding Paper
OPEN

Can Learned Optimization Make Reinforcement Learning Less Difficult?

Alexander D. Goldie, Chris Lu, Matthew T. Jackson, Shimon Whiteson, Jakob N. Foerster

NeurIPS 2024 · Spotlight

Also Spotlight at the AutoRL Workshop, ICML 2024.

Other Publications