Skip to content

Instantly share code, notes, and snippets.

@simoninithomas

simoninithomas/Dueling Deep Q Learning with Doom (+ double DQNs and Prioritized Experience Replay).ipynb

Last active February 26, 2020 13:37
Show Gist options
  • Save simoninithomas/d6adc6edb0a7f37d6323a5e3d2ab72ec to your computer and use it in GitHub Desktop.
Save simoninithomas/d6adc6edb0a7f37d6323a5e3d2ab72ec to your computer and use it in GitHub Desktop.
Download ZIP
Display the source blob
Display the rendered blob
Raw
Dueling Deep Q Learning with Doom (+ double DQNs and Prioritized Experience Replay).ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@Parkertao
Copy link

Parkertao commented Aug 1, 2018 •
edited
Loading

Hi, Thomas Simonini, thank you for your code, but when I tried to modify it and run, I got a issue that the value of loss is always 0. I apologize for my poor English ,and I am really confused.
I found the ISWeights_mb is [[0],[0],...[0]],and I guess that's the cause of this issue.

@chenwaipui
Copy link

I think there is a typo, you normalize the fame but then u did not use the normalize one

@ndeshp2s
Copy link

ndeshp2s commented Mar 3, 2019 •
edited
Loading

@Parkertao Did you manage to solve the issue of ISWeights_mb (and eventually of loss)?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment