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

[Feature] Prioritized Replay Buffer #160

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

gliese876b
Copy link

@gliese876b gliese876b commented Jan 10, 2025

An option to use Prioritized Replay Buffer for off-policy algorithms is added with two parameters as alpha and beta.

fixes #158

@facebook-github-bot
Copy link

Hi @gliese876b!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at [email protected]. Thanks!

Copy link
Collaborator

@matteobettini matteobettini left a comment

Choose a reason for hiding this comment

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

Looks great! Ty for typos :)

@@ -54,7 +54,7 @@ max_n_frames: 3_000_000
on_policy_collected_frames_per_batch: 6000
# Number of environments used for collection
# If the environment is vectorized, this will be the number of batched environments.
# Otherwise batching will be simulated and each env will be run sequentially or parallely depending on parallel_collection.
# Otherwise batching will be simulated and each env will be run sequentially or parallel depending on parallel_collection.
Copy link
Collaborator

Choose a reason for hiding this comment

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

parallelly?

Copy link
Author

Choose a reason for hiding this comment

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

Not my best choice but I guess parallelly seems ok :)



evaluation: True
# Whether to render the evaluation (if rendering is available)
render: True
render: False
Copy link
Collaborator

Choose a reason for hiding this comment

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

i would keep this true by default as users like to see videos

Copy link
Author

Choose a reason for hiding this comment

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

Oh sorry, missed that. I had some codec issues on few servers so I changed it to False. Default value of True is fine!

@matteobettini matteobettini changed the title Prioritized Replay Buffer option is added [Feature] Prioritized Replay Buffer Jan 10, 2025
@facebook-github-bot
Copy link

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!

@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 Jan 10, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
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
Development

Successfully merging this pull request may close these issues.

Prioritized Replay Buffer for Off-policy Algorithms
3 participants