Skip to content
forked from EMI-Group/evox

Distributed GPU-Accelerated Framework for Evolutionary Computation. Comprehensive Library of Evolutionary Algorithms & Benchmark Problems.

License

Notifications You must be signed in to change notification settings

ranchengcn/evox

 
 

Repository files navigation

EvoX Logo

EvoX Paper on arXiv EvoX Documentation EvoX Build Status

🌟Distributed GPU-accelerated Framework for Scalable Evolutionary Computation🌟


Building upon JAX and Ray, EvoX offers a comprehensive suite of 50+ Evolutionary Algorithms (EAs) and a wide range of 100+ Benchmark Problems, all benefiting from distributed GPU-acceleration. It facilitates efficient exploration of complex optimization landscapes, effective tackling of black-box optimization challenges, and deep dives into neuroevolution with Brax. With a foundation in functional programming and hierarchical state management, EvoX offers a user-friendly and modular experience. For more details, please refer to our Paper and Documentation.


Key Features

  • 🚀 Fast Performance:

    • Experience GPU-Accelerated optimization, achieving speeds 100x faster than traditional methods.
    • Leverage the power of Distributed Workflows for even more rapid optimization.
  • 🌐 Versatile Optimization Suite:

    • Cater to all your needs with both Single-objective and Multi-objective optimization capabilities.
    • Dive into a comprehensive library of Benchmark Problems, ensuring robust testing and evaluation.
    • Explore the frontier of AI with extensive tools for Neuroevolution tasks.
  • 🛠️ Designed for Simplicity:

    • Embrace the elegance of Functional Programming, simplifying complex algorithmic compositions.
    • Benefit from Hierarchical State Management, ensuring modular and clean programming.
    • Jumpstart your journey with our Detailed Tutorial.

Comprehensive Evolutionary Algorithms

Single-Objective Optimization

Category Algorithm Names
Differential Evolution CoDE, JaDE, SaDE, SHADE, IMODE, ...
Evolution Strategies CMA-ES, PGPE, OpenES, CR-FM-NES, xNES, ...
Particle Swarm Optimization FIPS, CSO, CPSO, CLPSO, SL-PSO, ...

Multi-Objective Optimization

Category Algorithm Names
Dominance-based NSGA-II, NSGA-III, SPEA2, BiGE, KnEA, ...
Decomposition-based MOEA/D, RVEA, t-DEA, MOEAD-M2M, EAG-MOEAD, ...
Indicator-based IBEA, HypE, SRA, MaOEA-IGD, AR-MOEA, ...

For a comprehensive list and further details of all algorithms, please check the API Documentation.

Diverse Benchmark Problems

Category Problem Names
Numerical DTLZ, LSMOP, MaF, ZDT, CEC'22, ...
Neuroevolution Brax, Gym, TorchVision Dataset, ...

For a comprehensive list and further details of all benchmark problems, please check the API Documentation.

Setting Up EvoX

Install evox effortlessly via pip:

pip install evox

Note: To install EvoX with JAX and hardware acceleration capabilities, please refer to our comprehensive Installation Guide.

Quick Start

Kickstart your journey with EvoX in just a few simple steps:

  1. Import necessary modules:
import evox
from evox import algorithms, problems, workflows
  1. Configure an algorithm and define a problem:
pso = algorithms.PSO(
    lb=jnp.full(shape=(2,), fill_value=-32),
    ub=jnp.full(shape=(2,), fill_value=32),
    pop_size=100,
)
ackley = problems.numerical.Ackley()
  1. Compose and initialize the workflow:
workflow = workflows.StdWorkflow(pso, ackley)
key = jax.random.PRNGKey(42)
state = workflow.init(key)
  1. Run the workflow:
# Execute the workflow for 100 iterations
for i in range(100):
    state = workflow.step(state)

Use-cases and Applications

Try out ready-to-play examples in your browser with Colab:

Example Link
Basic Usage Open in Colab
Numerical Optimization Open in Colab
Neuroevolution with Gym Open in Colab
Neuroevolution with Brax Open in Colab
Custom Algorithm/Problem Open in Colab

For more use-cases and applications, pleae check out Example Directory.

Community & Support

  • Engage in discussions and share your experiences on GitHub Discussion Board.
  • Join our QQ group (ID: 297969717).
  • Help with the translation of the documentation on Weblate.

Translation status

Sister Projects

  • EvoXBench: A benchmark platform for Neural Architecutre Search (NAS) without the requirement of GPUs/PyTorch/Tensorflow, supporting various programming languages such as Java, Matlab, Python, ect. Check out here.

Citing EvoX

If you use EvoX in your research and want to cite it in your work, please use:

@article{evox,
  title = {{EvoX}: {A} {Distributed} {GPU}-accelerated {Framework} for {Scalable} {Evolutionary} {Computation}},
  author = {Huang, Beichen and Cheng, Ran and Li, Zhuozhao and Jin, Yaochu and Tan, Kay Chen},
  journal = {arXiv preprint arXiv:2301.12457},
  eprint = {2301.12457},
  year = {2023}
}

About

Distributed GPU-Accelerated Framework for Evolutionary Computation. Comprehensive Library of Evolutionary Algorithms & Benchmark Problems.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 99.6%
  • Nix 0.4%