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] Improve off-policy training #16

Merged
merged 12 commits into from
Sep 26, 2023
Merged

[Feature] Improve off-policy training #16

merged 12 commits into from
Sep 26, 2023

Conversation

matteobettini
Copy link
Collaborator

This PR presents many improvements for off-policy training:

  • now users can choose between soft or hard target updates
  • now users can control the init and end exploration epsilon

Signed-off-by: Matteo Bettini <[email protected]>
Signed-off-by: Matteo Bettini <[email protected]>
Signed-off-by: Matteo Bettini <[email protected]>
Signed-off-by: Matteo Bettini <[email protected]>
Signed-off-by: Matteo Bettini <[email protected]>
Signed-off-by: Matteo Bettini <[email protected]>
Signed-off-by: Matteo Bettini <[email protected]>
Signed-off-by: Matteo Bettini <[email protected]>
@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 26, 2023
@matteobettini matteobettini changed the title [BugFix] Improve off-policy training [Feature] Improve off-policy training Sep 26, 2023
@matteobettini matteobettini merged commit 7f35824 into main Sep 26, 2023
9 of 12 checks passed
@matteobettini matteobettini deleted the iql_comparison branch September 26, 2023 10:13
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.

2 participants