Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
Name
frans-kvfrans-meng-eecs-2023-thesis.pdf
Description
Thesis PDF
Size
11.66 MB
Format
Adobe PDF
Checksum (MD5)
cff1b54b89b64c5388398a38f3299953
Author(s)
Frans, Kevin
Advisor(s)
Isola, Phillip
Date Issued
June 2023
Publisher
Massachusetts Institute of Technology
Abstract
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 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.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
