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.

Sign up for GitHub

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

Jump to bottom

[BugFix] Fix DDPG squeezing #1487

Merged
merged 5 commits into from
Sep 7, 2023
Merged

[BugFix] Fix DDPG squeezing #1487

merged 5 commits into from
Sep 7, 2023

Conversation

matteobettini
Copy link
Contributor

@matteobettini matteobettini commented Sep 5, 2023 •
edited
Loading

There is a line in DDPG which unsqueezes according to the batch_size of a tensordict which is not compatible when the tensor has a multiagent dimension outside the tesnordict batch_size

Fixes #1486

@matteobettini
fix ddpg
b741716 
Signed-off-by: Matteo Bettini <matbet@meta.com>
@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Sep 5, 2023
@vmoens vmoens added the bug Something isn't working label Sep 5, 2023
@matteobettini matteobettini marked this pull request as ready for review September 5, 2023 19:31
@matteobettini
amend
fc1d3c9 
Signed-off-by: Matteo Bettini <matbet@meta.com>
vmoens
vmoens reviewed Sep 6, 2023
View reviewed changes
Copy link
Contributor

@vmoens vmoens left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think that this will cause issues with prioritized RBs but I might be wrong. Worth checking and if it is the case we should add a test and consider a broader fix

@matteobettini
Copy link
Contributor Author

ok what kind of issue do you think I should try to look for?

@vmoens vmoens merged commit d8504e7 into pytorch:main Sep 7, 2023
@matteobettini matteobettini deleted the fixmaddpg branch September 7, 2023 14:30
vmoens pushed a commit to hyerra/rl that referenced this pull request Oct 10, 2023
@matteobettini @vmoens
[BugFix] Fix DDPG squeezing (pytorch#1487)
c0144fe 
Signed-off-by: Matteo Bettini <matbet@meta.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@vmoens vmoens vmoens approved these changes

Assignees
No one assigned
Labels
bug Something isn't working CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

[BUG] Unsqueezing the error in ddpg
3 participants
@matteobettini @vmoens @facebook-github-bot