EvoTorch is an evolutionary optimization framework built on top of PyTorch, developed by NNAISENSE. It is designed for large-scale optimization problems, particularly those that require evolutionary algorithms rather than gradient-based methods.
Features
- Implements various evolutionary optimization algorithms like CMA-ES and NES
- Designed for high-dimensional and complex optimization problems
- Leverages PyTorch for seamless GPU acceleration
- Supports distributed computing for scaling evolutionary training
- Provides easy-to-use APIs for defining custom optimization problems
- Suitable for neural architecture search, reinforcement learning, and black-box optimization
Categories
Reinforcement Learning LibrariesLicense
Apache License V2.0Follow EvoTorch
Other Useful Business Software
Veeam Data Platform v13.1 - Get Your Free Trial
Try Veeam Data Platform today. Experience the unified platform that's secure by design, portable by default, and proven to recover clean, fast, and anywhere.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of EvoTorch!