Popular GitHub Repositories for Evolutionary Algorithms

Source code of PyGAD, a Python 3 library for building the genetic algorithm and training machine learning algorithms (Keras & PyTorch).

A 2D Unity simulation in which cars learn to navigate themselves through different courses. The cars are steered by a feedforward neural network. The weights of the network are trained using a modified genetic algorithm.

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

Distributed High-Performance Symbolic Regression in Julia

Automated modeling and machine learning framework FEDOT

EvoloPy toolbox provides classical and recent nature-inspired metaheuristic for the global optimization.

Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.

A General Automated Machine Learning framework to simplify the development of End-to-end AutoML toolkits in specific domains.

A collection of Deep Neuroevolution resources or evolutionary algorithms applying in Deep Learning (constantly updating)

A bare-bones Python library for quality diversity optimization.

A fast and flexible evolution engine for implementing artificial evolution and genetic programming techniques

[ECCV2020] NSGANetV2: Evolutionary Multi-Objective Surrogate-Assisted Neural Architecture Search

Transforming Neural Architecture Search (NAS) into multi-objective optimization problems. A benchmark suite for testing evolutionary algorithms in deep learning.

[ICML 2020] Prediction-Guided Multi-Objective Reinforcement Learning for Continuous Robot Control

MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning (https://proceedings.neurips.cc/paper_files/paper/2023/hash/232eee8ef411a0a316efa298d7be3c2b-Abstract-Datasets_and_Benchmarks.html)

Contains an implementation (sklearn API) of the algorithm proposed in "GENDIS: GEnetic DIscovery of Shapelets" and code to reproduce all experiments.

The first autonomous computer program that can do anything to earn money without human operators.

Train PyTorch Models using the Genetic Algorithm with PyGAD

Python framework for automated time series classification, regression and forecasting

EvoRL is a fully GPU-accelerated framework for Evolutionary Reinforcement Learning, implemented with JAX. It supports Reinforcement Learning (RL), Evolutionary Computation (EC), Evolution-guided Reinforcement Learning (ERL), AutoRL, and seamless integration with GPU-optimized simulation environments.