QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Acceleration
This provides a modular and accelerated library for researchers and practitioners in optimization and AI, though it is incremental as it builds on existing QD and Jax frameworks.
The authors tackled the need for efficient and user-friendly tools for Quality-Diversity optimization by developing QDax, an open-source library in Jax that supports hardware acceleration, achieving 95% test coverage and enabling versatile applications from black-box optimization to continuous control.
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.