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

Save top n models per checkpoint #24

Open
danielgafni opened this issue Apr 1, 2022 · 0 comments
Open

Save top n models per checkpoint #24

danielgafni opened this issue Apr 1, 2022 · 0 comments

Comments

@danielgafni
Copy link
Contributor

danielgafni commented Apr 1, 2022 •
edited
Loading

As I understand, currently only the best model from the population is being saved in the end of the iteration. This may lead to inconsistent train/test results (due to overfitting) in some setups. Blending the top n models could potentially reduce this effect.

Would you be interested in this feature for evojax? I can work on a PR. Seems like not all solvers can have this feature.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@danielgafni