Skip to content

Instantly share code, notes, and snippets.

@elumixor

elumixor/TRPO_critic.py

Created May 24, 2020 22:39
Show Gist options
  • Save elumixor/39829d34ce52318a7defa7fcd10a7601 to your computer and use it in GitHub Desktop.
Save elumixor/39829d34ce52318a7defa7fcd10a7601 to your computer and use it in GitHub Desktop.
Download ZIP
TRPO critic network
Raw
TRPO_critic.py
# Critic takes a state and returns its values
critic_hidden = 32
critic = nn.Sequential(nn.Linear(obs_shape[0], critic_hidden),
nn.ReLU(),
nn.Linear(critic_hidden, 1))
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment