1

Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning
Benchmarks play a crucial role in the development and analysis of reinforcement learning (RL) algorithms. We identify that existing …
Michael Matthews, Michael Beukman, Benjamin Ellis, Mikayel Samvelyan, Matthew Jackson, Samuel Coward, Jakob Foerster
PDF Cite
Policy-Guided Diffusion
In many real-world settings, agents must learn from an offline dataset gathered by some prior behavior policy. Such a setting naturally …
Matthew Jackson, Michael Matthews, Cong Lu, Benjamin Ellis, Jakob Foerster
PDF Cite
Refining Minimax Regret for Unsupervised Environment Design
In many real-world settings, agents must learn from an offline dataset gathered by some prior behavior policy. Such a setting naturally …
Michael Beukman, Samuel Coward, Michael Matthews, Mattie Fellows, Minqi Jiang, Michael Dennis, Jakob Foerster
PDF Cite
Hierarchical Kickstarting for Skill Transfer in Reinforcement Learning
Practising and honing skills forms a fundamental component of how humans learn, yet artificial agents are rarely specifically trained …
Michael Matthews, Mikayel Samvelyan, Jack Parker-Holder, Edward Grefenstette, Tim Rocktäschel
PDF Cite