search

andyzeng / visual-pushing-grasping

Train robotic agents to learn to plan pushing and grasping actions for manipulation with deep reinforcement learning.
http://vpg.cs.princeton.edu/
BSD 2-Clause "Simplified" License
898 stars 315 forks source link

Target Network #32

Open mike112223 opened 5 years ago

mike112223 commented 5 years ago

Hi Andy! In paper, you say you use fixed target network to get Q-target value. However, I didn't find this part in code. So did you implement it in code?

gbyuHub commented 4 years ago

I had the same problem, and still no idea. Differences between thesis and real code?

chungshan commented 4 years ago

I had the same problem, too. @andyzeng

TriBall3 commented 3 years ago

I had the same problem, too. I don't see the target network and eval network from the code, I just see that the parameters of GraspNet and PushNet are changing all the time.@andyzeng

Focusssss commented 3 years ago

@virtualclone @mike112223 @FisherguanbaoYu @TriBall3 @ahundt please how to solve the problem as you said, thanks!!!