Deep-Q-Learning-Paper-To-Code icon indicating copy to clipboard operation
Deep-Q-Learning-Paper-To-Code copied to clipboard
verified publisher icon philtabor

Detach target nexwork in DQN

Open yangyi0318 opened this issue 5 years ago • 0 comments

In DQNAgent, I think you may need to call detach() at line 90 to detach the target network from gradient evaluation.

yangyi0318 avatar Oct 17 '20 06:10 yangyi0318