QDax: A library for quality-diversity and population-based algorithms with hardware acceleration
File(s)23-1027.pdf (1.94 MB)
Published version
Author(s)
Type
Journal Article
Abstract
QDax is an open-source library with a streamlined and modular API for Quality-Diversity (QD) optimisation algorithms in Jax. The library serves as a versatile tool for optimisation purposes, ranging from black-box optimisation to continuous control. QDax offers implementations of popular QD, Neuroevolution, and Reinforcement Learning (RL) algorithms, supported by various examples. All the implementations can be just-in-time compiled with Jax, facilitating efficient execution across multiple accelerators, including GPUs and TPUs. These implementations effectively demonstrate the framework's flexibility and user-friendliness, easing experimentation for research purposes. Furthermore, the library is thoroughly documented and has 93% test coverage.
Date Issued
2024-05-01
Date Acceptance
2024-03-26
ISSN
1532-4435
Publisher
Microtome Publishing
Start Page
1
End Page
16
Journal / Book Title
Journal of Machine Learning Research
Volume
25
Issue
108
Copyright Statement
©2024 Felix Chalumeau*, Bryan Lim*, Rapha¨el Boige, Maxime Allard, Luca Grillotti, Manon Flageat, Valentin
Mac´e, Guillaume Richard, Arthur Flajolet, Thomas Pierrot**, Antoine Cully**.
License: CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/. Attribution requirements are provided
at http://jmlr.org/papers/v25/23-1027.html
Mac´e, Guillaume Richard, Arthur Flajolet, Thomas Pierrot**, Antoine Cully**.
License: CC-BY 4.0, see https://creativecommons.org/licenses/by/4.0/. Attribution requirements are provided
at http://jmlr.org/papers/v25/23-1027.html
Identifier
https://www.jmlr.org/papers/v25/23-1027.html
Publication Status
Published