Lilian Weng 9/5/2019

Evolution Strategies

Read Original

This technical article explores Evolution Strategies (ES), a class of black-box optimization algorithms within the evolutionary algorithms family. It contrasts ES with gradient-based methods like SGD, explains the core concepts of ES including the Simple Gaussian ES, and discusses its application in optimizing deep reinforcement learning models where gradient computation is difficult.

Evolution Strategies

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week

1
The Beautiful Web
Jens Oliver Meiert 2 votes
3
LLM Use in the Python Source Code
Miguel Grinberg 1 votes
4
Wagon’s algorithm in Python
John D. Cook 1 votes