TensorNEAT: A GPU-accelerated Library for NeuroEvolution of Augmenting Topologies

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Lishuang, Zhao, Mengfei, Liu, Enyu, Sun, Kebin, Cheng, Ran
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917982525980672
author Wang, Lishuang
Zhao, Mengfei
Liu, Enyu
Sun, Kebin
Cheng, Ran
author_facet Wang, Lishuang
Zhao, Mengfei
Liu, Enyu
Sun, Kebin
Cheng, Ran
contents The NeuroEvolution of Augmenting Topologies (NEAT) algorithm has received considerable recognition in the field of neuroevolution. Its effectiveness is derived from initiating with simple networks and incrementally evolving both their topologies and weights. Although its capability across various challenges is evident, the algorithm's computational efficiency remains an impediment, limiting its scalability potential. To address these limitations, this paper introduces TensorNEAT, a GPU-accelerated library that applies tensorization to the NEAT algorithm. Tensorization reformulates NEAT's diverse network topologies and operations into uniformly shaped tensors, enabling efficient parallel execution across entire populations. TensorNEAT is built upon JAX, leveraging automatic function vectorization and hardware acceleration to significantly enhance computational efficiency. In addition to NEAT, the library supports variants such as CPPN and HyperNEAT, and integrates with benchmark environments like Gym, Brax, and gymnax. Experimental evaluations across various robotic control environments in Brax demonstrate that TensorNEAT delivers up to 500x speedups compared to existing implementations, such as NEAT-Python. The source code for TensorNEAT is publicly available at: https://github.com/EMI-Group/tensorneat.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08339
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TensorNEAT: A GPU-accelerated Library for NeuroEvolution of Augmenting Topologies
Wang, Lishuang
Zhao, Mengfei
Liu, Enyu
Sun, Kebin
Cheng, Ran
Neural and Evolutionary Computing
The NeuroEvolution of Augmenting Topologies (NEAT) algorithm has received considerable recognition in the field of neuroevolution. Its effectiveness is derived from initiating with simple networks and incrementally evolving both their topologies and weights. Although its capability across various challenges is evident, the algorithm's computational efficiency remains an impediment, limiting its scalability potential. To address these limitations, this paper introduces TensorNEAT, a GPU-accelerated library that applies tensorization to the NEAT algorithm. Tensorization reformulates NEAT's diverse network topologies and operations into uniformly shaped tensors, enabling efficient parallel execution across entire populations. TensorNEAT is built upon JAX, leveraging automatic function vectorization and hardware acceleration to significantly enhance computational efficiency. In addition to NEAT, the library supports variants such as CPPN and HyperNEAT, and integrates with benchmark environments like Gym, Brax, and gymnax. Experimental evaluations across various robotic control environments in Brax demonstrate that TensorNEAT delivers up to 500x speedups compared to existing implementations, such as NEAT-Python. The source code for TensorNEAT is publicly available at: https://github.com/EMI-Group/tensorneat.
title TensorNEAT: A GPU-accelerated Library for NeuroEvolution of Augmenting Topologies
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2504.08339