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

[REQUEST] Annealing schedule of hyperparameters #410

Open
peymvn opened this issue Aug 17, 2024 · 1 comment
Open

[REQUEST] Annealing schedule of hyperparameters #410

peymvn opened this issue Aug 17, 2024 · 1 comment
Labels
enhancement New feature or request

Comments

@peymvn
Copy link

peymvn commented Aug 17, 2024

Hello,
Thank you for this great work! I’ve been working with an algorithm very similar to CQL, but with a key difference: we require annealing schedules for the hyperparameters (e.g., adjusting the conservative alpha at each step). I didn’t see this feature in your implementation.
I would be grateful if you could let me know whether this has already been implemented. If not, what do you think would be the best approach to add this functionality?
Thank you for your guidance!

@peymvn peymvn added the enhancement New feature or request label Aug 17, 2024
@takuseno
Copy link
Owner

@peymvn Thanks for the issue. Currently, it's not supported by default. However, there is a workaround to anneal learning rates:

# workaround for learning scheduler

You can try this in your experiments with the current version of d3rlpy.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants