collaborators

6 papers

cs.LG2026

DiscoGen: Procedural Generation of Algorithm Discovery Tasks in Machine Learning

Alexander D. Goldie, Zilin Wang, Adrian Hayler +17

Automating the development of machine learning algorithms has the potential to unlock new breakthroughs. However, our ability to improve and evaluate algorithm discovery systems ha…

cs.LG2026

High entropy leads to symmetry-equivariant policies in Dec-POMDPs

Johannes Forkel, Constantin Ruhdorfer, Michael Beukman +2

We prove that in any Dec-POMDP, sufficiently high entropy regularization ensures that the policy gradient flow with tabular softmax parametrization always converges, for any initia…

cs.LG2026

Goal-Conditioned Agents that Learn Everything All at Once

Michael Matthews, Matthew Jackson, Michael Beukman +5

A goal-conditioned reinforcement learning agent exploring an environment will see a wealth of information throughout a trajectory, most of which is discarded when only performing o…

cs.LG2026

Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel Environments

Michael Beukman, Khimya Khetarpal, Zeyu Zheng +4

An agent's performance stagnating at a suboptimal level is a common problem in deep on-policy RL. Focusing on PPO, we show that plateaus in certain regimes arise not because of kno…

cs.LG2025

An Optimisation Framework for Unsupervised Environment Design

Nathan Monette, Alistair Letcher, Michael Beukman +4

For reinforcement learning agents to be deployed in high-risk settings, they must achieve a high level of robustness to unfamiliar scenarios. One method for improving robustness is…

cs.LG2025

Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks

Michael Matthews, Michael Beukman, Chris Lu +1

While large models trained with self-supervised learning on offline datasets have shown remarkable capabilities in text and image domains, achieving the same generalisation for age…