Reinforcement-Learning icon indicating copy to clipboard operation
Reinforcement-Learning copied to clipboard

Published 20 hours ago • verified publisher icon andri27-ts

Updating target network - Potential Bug

Open sai-prasanna opened this issue 3 years ago • 0 comments

https://github.com/andri27-ts/Reinforcement-Learning/blob/c57064f747f51d1c495639c7413f5a2be01acd5f/Week3/central_control.py#L55

After loading the parameters of the moving network into the target network, why is the target network reference pointing to the moving network? Wouldn't this make the target network track the moving network in every update and make it ineffective?

sai-prasanna avatar Jan 26 '21 06:01 sai-prasanna