pretrained model is needed
Opened this issue · 4 comments
The training process is too slow...
Does someone have the pretrained model???It's emergency.
After I replace this code with my own data set, my reward does not converge. Have you ever been in this situation? Can you help me?
After I replace this code with my own data set, my reward does not converge. Have you ever been in this situation? Can you help me?
I'm sorry that I only used the dataset provided by the author and reward converges as expected. By the way, do you have the pretrained model for the original dataset? I'd be appreciated if you can help me with that.
After I replace this code with my own data set, my reward does not converge. Have you ever been in this situation? Can you help me?
I'm sorry that I only used the dataset provided by the author and reward converges as expected. By the way, do you have the pretrained model for the original dataset? I'd be appreciated if you can help me with that.
I just learned DDQN, so I don't understand what you mean by training model. I'm sorry I can't help you.
I found that the author's reward is also not converging. Would you mind letting me have a look at your reward effect picture?
I really need your help with my paper, thank you very much!!!