Skip to content

Instantly share code, notes, and snippets.

@elumixor

elumixor/TRPO_surrogate_loss.py

Created May 24, 2020 23:25
Show Gist options
  • Save elumixor/2db2ea2199fd921a7bdbb57a46e4566f to your computer and use it in GitHub Desktop.
Save elumixor/2db2ea2199fd921a7bdbb57a46e4566f to your computer and use it in GitHub Desktop.
Download ZIP
Raw
TRPO_surrogate_loss.py
def surrogate_loss(new_probabilities, old_probabilities, advantages):
return (new_probabilities / old_probabilities * advantages).mean()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment