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

[Hyper param tuning - early stop / green penalty] #68

Open
wants to merge 8 commits into
base: ppo-hyperparam-tuning
Choose a base branch
from
Open

[Hyper param tuning - early stop / green penalty] #68

wants to merge 8 commits into from

Conversation

xeviknal
Copy link
Owner

Adding hyperparameter tuning with extra wrappers:

  • early stop - finish the environment when the avg reward of the latest N steps is negative (similar to a curriculum learning)
  • green-penalty - reduce the rewards when the car is in the grass (reward -0.15 instead of -0.1).

See the tuning trails in the following comments.

@xeviknal
Copy link
Owner Author

xeviknal commented Apr 18, 2021 •
edited

First experiment:
legend-juanjo-train_2021-04-14_22-37-25
tuning-juanjo-train_2021-04-14_22-37-25

@xeviknal
Copy link
Owner Author

xeviknal commented Apr 18, 2021 •
edited

Second experiment:
legend-juanjo-train_2021-04-15_09-52-01
tuning-juanjo-train_2021-04-15_09-52-01

@xeviknal
Copy link
Owner Author

Third experiment:
legend-juanjo-train_2021-04-16_20-18-59
tuning-juanjo-train_2021-04-16_20-18-59

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
1 participant
@xeviknal