Evolution Strategies Python Packages

cmaes

Python library for CMA Evolution Strategy.

gradient-free-optimizers

Lightweight optimization with local, global, population-based and sequential techniques across mixed search spaces

pypop7

[JMLR (CCF-A)] PyPop7: A Pure-PYthon LibrarY for POPulation-based Black-Box Optimization (BBO), especially *Large-Scale* algorithm variants. In the near future, we will add Learning-Based Optimizers as its extensions. [https://jmlr.org/papers/v25/23-0386.html]

llm4ad-next

A next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use

seamaze

Classical, Limited-Memory, and Dynamical Low-Rank CMA-ES Variants for Efficient Black-Box Optimization

evopy

Evolutionary Strategies made simple!

crfmnes

(CEC2022) Fast Moving Natural Evolution Strategy for High-Dimensional Problems

evostra

A fast Evolution Strategy implementation in Python

fingym

A tool for developing reinforcement learning algorithms focused in stock prediction

eggroll-es

Gradient-free fine-tuning for any HuggingFace model. EGGROLL Evolution Strategies in PyTorch. No backprop. No gradients. Just evolution.

nes-torch

Minimal PyTorch Library for Natural Evolution Strategies

estorch

Evolution Strategy Library

mevo

Evolutionary algorithms, alternative to Reinforcement Learning

pepg-es

Python Implementation of Parameter-exploring Policy Gradients Evolution Strategy

pytorch-optimize

A simple black-box optimization framework to train your pytorch models for optimizing non-differentiable objectives