Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
This work addresses the research bottleneck of creating rich task distributions for studying generalization in reinforcement learning, though it is incremental as it builds on existing platform development efforts.
The paper tackles the challenge of generalization in reinforcement learning by introducing Powderworld, a GPU-based simulation environment that supports diverse tasks, and finds that increasing environmental complexity improves generalization for world models and some agents but can hinder learning in high-variance settings.
One of the grand challenges of reinforcement learning is the ability to generalize to new tasks. However, general agents require a set of rich, diverse tasks to train on. Designing a `foundation environment' for such tasks is tricky -- the ideal environment would support a range of emergent phenomena, an expressive task space, and fast runtime. To take a step towards addressing this research bottleneck, this work presents Powderworld, a lightweight yet expressive simulation environment running directly on the GPU. Within Powderworld, two motivating challenges distributions are presented, one for world-modelling and one for reinforcement learning. Each contains hand-designed test tasks to examine generalization. Experiments indicate that increasing the environment's complexity improves generalization for world models and certain reinforcement learning agents, yet may inhibit learning in high-variance environments. Powderworld aims to support the study of generalization by providing a source of diverse tasks arising from the same core rules.