这是indexloc提供的服务,不要输入任何密码
Skip to content

final fix for actor_critic shared head parameters #458

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

Merged
merged 3 commits into from
Oct 4, 2021

Conversation

Trinkle23897
Copy link
Collaborator

@Trinkle23897 Trinkle23897 mentioned this pull request Oct 4, 2021
8 tasks
@Trinkle23897 Trinkle23897 merged commit 5df6480 into thu-ml:master Oct 4, 2021
@Trinkle23897 Trinkle23897 deleted the reproducibility branch October 4, 2021 15:19
@Trinkle23897 Trinkle23897 linked an issue Oct 4, 2021 that may be closed by this pull request
8 tasks
@ultmaster
Copy link
Contributor

This PR causes tianshou 0.4.4 fails to load checkpoints that was previously trained on tianshou 0.4.3.

I think a simple conversion is needed. Post it here in case anyone needs it.

data = torch.load('previous.pth')
for k in list(data.keys()):
    data['_actor_critic.' + k] = data[k]
torch.save(data, 'new.pth')

@Trinkle23897
Copy link
Collaborator Author

Thanks, let me convert it to an issue.

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.

Reproduce problem on training
2 participants