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

Resume from checkpoint #36

Closed
belerico opened this issue Jun 9, 2023 · 0 comments · Fixed by #95
Closed

Resume from checkpoint #36

belerico opened this issue Jun 9, 2023 · 0 comments · Fixed by #95
Labels
enhancement New feature or request

Comments

@belerico
Copy link
Member

belerico commented Jun 9, 2023

It would be nice to have the possibility to resume the training from a checkpoint. For on-policy algorithm we can just load the model and restart the optimization; for an off-policy method we can choose to restart with the old buffer, if it has been saved, or to restart while collecting a bunch of trajectories with the trained policy and restart from there.
This should be a global utility.
@belerico belerico added the enhancement New feature or request label Jun 9, 2023
@michele-milesi michele-milesi linked a pull request Sep 15, 2023 that will close this issue
Feature/resume from checkpoint #95
Merged
4 tasks
@michele-milesi michele-milesi mentioned this issue Sep 15, 2023
Merged
4 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Feature/resume from checkpoint Eclectic-Sheep/sheeprl
1 participant
@belerico