The agent's current position is denoted as 
and is initially picked at random from the entire search-space. The potential new position is denoted as 
and is sampled from the neighborhood of 
by letting 
, where 
is a random vector picked ...
How it works
Get Hands-On Neural Network Programming with C# now with O’Reilly online learning.
O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.