Feature/20240911 enable squashed gaussian on ppo #130
Merged
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
ishihara-y
force-pushed
the
feature/20240911-enable-squashed-gaussian-on-ppo
branch
from
92b0df8
to
03908bc
Compare
|
LGTM. |
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Outdated suggestions cannot be applied.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.
Some distribution (like SquashedGaussian) does not have an analytical form for the entropy. Thus PPO can not use such distribution in the training.
However, when entropy coefficient of PPO training is 0, ppo does not need to compute the entropy of the policy distribution.
This PR enables using SquashedGaussian and other distributions in PPO when the entropy coefficient is 0.
New implementation ignores the computation of entropy in policy training with 0 coefficient.