EvoTorch: Scalable Evolutionary Computation in Python

Nihat Engin Toklu, Timothy Atkinson, Vojtěch Micka, Paweł Liskowski, Rupesh Kumar Srivastava
2/24/2023
cs.NEcs.AI

No official code found. Best implementation: nnaisense/evotorch (1,146 stars, Apache-2.0, PyTorch, last commit 2026-04-27).

Abstract

Evolutionary computation is an important component within various fields such as artificial intelligence research, reinforcement learning, robotics, industrial automation and/or optimization, engineering design, etc. Considering the increasing computational demands and the dimensionalities of modern optimization problems, the requirement for scalable, re-usable, and practical evolutionary algorithm implementations has been growing. To address this requirement, we present EvoTorch: an evolutionary computation library designed to work with high-dimensional optimization problems, with GPU support and with high parallelization capabilities. EvoTorch is based on and seamlessly works with the PyTorch library, and therefore, allows the users to define their optimization problems using a well-known API.

View on arXivView PDF

Code Implementations(1)

nnaisense/evotorchCommunity100%
PyTorchApache-2.0

Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.

1,14679Python5 months agoApache-2.0
artificial-intelligencedistributedevolutionary-algorithmsevolutionary-computationgpu+7 more

Similar Papers

CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning

85% match1 repo3262025

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

85% match1 repo3612023

DECN: Evolution Inspired Deep Convolution Network for Black-box Optimization

84% match2023

Evolutionary Reinforcement Learning: A Survey

84% match2023

Large Language Model-Powered Evolutionary Code Optimization on a Phylogenetic Tree

84% match2026

The Paradox of Success in Evolutionary and Bioinspired Optimization: Revisiting Critical Issues, Key Studies, and Methodological Pathways

83% match2025

Cite this paper

@article{toklu2023evotorch,
  title  = {EvoTorch: Scalable Evolutionary Computation in Python},
  author = {Nihat Engin Toklu and Timothy Atkinson and Vojtěch Micka and Paweł Liskowski and Rupesh Kumar Srivastava},
  year   = {2023},
  eprint = {2302.12600},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2302.12600v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2302.12600.svg)](https://codeofpaper.com/paper/2302.12600)

Discussion