Create optimizer in OnPolicyAlgorithm only after the device is set
#1771
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
cmangla
changed the title
OnPolicyAlgorithm only after the device is set
|
@araffin This is ready for the CI tests now and potentially also to merge. |
cmangla
commented
Dec 6, 2023
stable_baselines3/common/policies.py
Outdated
| @@ -885,6 +895,7 @@ def __init__( | |||
| normalize_images: bool = True, | |||
| optimizer_class: Type[th.optim.Optimizer] = th.optim.Adam, | |||
| optimizer_kwargs: Optional[Dict[str, Any]] = None, | |||
| _init_optimizer=True, # Currently unused, see PR #1771 | |||
There was a problem hiding this comment.
@araffin I'm currently testing enabling this one too. I will update this PR accordingly, hence switching it back to draft.
cmangla
force-pushed
the
pr-delay-ppo-optimizer
branch
from
4d07ede
to
daf9f7a
Compare
|
@araffin Looks good now |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Attempt to fix #1770 in a fully backward compatible manner.
Description
In PPO, the optimizer in the policy is created before the computation-device for the class is correctly set. This is a problem when the optimizer checks the target computation-device on initialization. This is a backward compatible fix.
Motivation and Context
Fixes #1770 . One can now use the
fusedoption in the Adam optimizer on CUDA devices, which, according to the documentation, is faster.Types of changes
Checklist
make format(required)make check-codestyleandmake lint(required)make pytestandmake typeboth pass. (required)make doc(required)