alirezamika/evostra
A fast Evolution Strategy implementation in Python
This project helps machine learning practitioners fine-tune the parameters of their neural networks to achieve better performance on a given task. You input your neural network's architecture and a function that calculates how well it's performing, and the system outputs optimized network weights. This is ideal for AI researchers and developers working on reinforcement learning or other complex optimization problems.
272 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need an efficient way to optimize the weights of a neural network or a similar model using an evolutionary strategy, especially when traditional gradient-based methods are difficult to apply.
Not ideal if you are looking for a simple, out-of-the-box solution for common machine learning tasks that already have well-established optimization algorithms.
Stars
272
Forks
48
Language
Python
License
MIT
Category
Last pushed
Apr 27, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/alirezamika/evostra"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
trevorstephens/gplearn
Genetic Programming in Python, with a scikit-learn inspired API
google/pyglove
Manipulating Python Programs
guofei9987/scikit-opt
Genetic Algorithm, Particle Swarm Optimization, Simulated Annealing, Ant Colony Optimization...
nnaisense/evotorch
Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.
esa/pagmo2
A C++ platform to perform parallel computations of optimisation tasks (global and local) via the...