Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add ability for DDPG to resume training, ensure observation to DDPG critic is flattened #937

Open
wants to merge 2 commits into
base: master
Choose a base branch
from

Conversation

williamjshipman
Copy link

Fixes two little things:

  1. Add saving and loading of all the variables used in DDPG, just like is done in A2C. This fixes DDPG does not support load_path parameter #935.
  2. baselines.ddpg.models.Critic wasn't ensuring that the observation and action have compatible dimensions before concatenating them. I've fixed this by adding an extra flatten applied to the observation input before the concatenation takes place.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

DDPG does not support load_path parameter
1 participant