nnaisense/evotorch

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

61
/ 100
Established

This tool helps researchers and engineers tackle challenging optimization problems, particularly in areas like reinforcement learning and black-box optimization, where traditional gradient-based methods aren't suitable. It takes your problem definition (an objective function or a reinforcement learning environment) and applies various evolutionary algorithms. The output is an optimized solution or a trained policy. It's designed for machine learning practitioners, AI researchers, and engineers working on complex control systems or model-free optimization.

1,123 stars. Available on PyPI.

Use this if you need to optimize complex systems, train AI agents in simulation, or solve problems where the relationship between inputs and outputs is not easily differentiable or understood (black-box scenarios).

Not ideal if your problem is well-suited for standard gradient-descent methods or if you are looking for a simple, out-of-the-box solution without any programming.

reinforcement-learning evolutionary-algorithms black-box-optimization AI-training robotics-control
Maintenance 10 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

1,123

Forks

77

Language

Python

License

Apache-2.0

Last pushed

Mar 09, 2026

Commits (30d)

0

Dependencies

8

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nnaisense/evotorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.