Pith. sign in

REVIEW 1 cited by

QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2308.03665 v1 pith:DEQ2MON3 submitted 2023-08-07 cs.AI cs.NE

Felix Chalumeau , Bryan Lim , Raphael Boige , Maxime Allard , Luca Grillotti , Manon Flageat , Valentin Macé , Arthur Flajolet
show 2 more authors
Thomas Pierrot Antoine Cully
This is my paper · ORCID
classification cs.AIcs.NE
keywords libraryalgorithmsimplementationsoptimizationqdaxpurposesquality-diversityacceleration
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

QDax is an open-source library with a streamlined and modular API for Quality-Diversity (QD) optimization algorithms in Jax. The library serves as a versatile tool for optimization purposes, ranging from black-box optimization 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 tested with 95\% coverage.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Scaling Policy Gradient Quality-Diversity with Massive Parallelization via Behavioral Variations

    cs.NE 2025-01 conditional novelty 6.0 of 10

    ASCII-ME replaces actor-critic updates in policy-gradient MAP-Elites with reward-weighted interpolation between action sequences, mapped to policy parameters through a Jacobian, enabling fast GPU-parallel quality-diversity.

Pith tools