6 papers
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…
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…
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…
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…
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…
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…