4 citations · 5 across the 11 of their papers we have counts for
6 papers · 1 filter
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…
JaxLife: An Open-Ended Agentic Simulator
Chris Lu, Michael Beukman, Michael Matthews +1
Human intelligence emerged through the process of natural selection and evolution on Earth. We investigate what it would take to re-create this process in silico. While past work h…
No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
Alexander Rutherford, Michael Beukman, Timon Willi +3
What data or environments to use for training to improve downstream performance is a longstanding and very topical question in reinforcement learning. In particular, Unsupervised E…
JaxUED: A simple and useable UED library in Jax
Samuel Coward, Michael Beukman, Jakob Foerster
We present JaxUED, an open-source library providing minimal dependency implementations of modern Unsupervised Environment Design (UED) algorithms in Jax. JaxUED leverages hardware…
Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning
Michael Matthews, Michael Beukman, Benjamin Ellis +4
Benchmarks play a crucial role in the development and analysis of reinforcement learning (RL) algorithms. We identify that existing benchmarks used for research into open-ended lea…
Refining Minimax Regret for Unsupervised Environment Design
Michael Beukman, Samuel Coward, Michael Matthews +4
In unsupervised environment design, reinforcement learning agents are trained on environment configurations (levels) generated by an adversary that maximises some objective. Regret…