Refactor JAX SAC agent's critic update to return gradients separately#426
Open
MorningFrog wants to merge 1 commit into
Open
Refactor JAX SAC agent's critic update to return gradients separately#426MorningFrog wants to merge 1 commit into
MorningFrog wants to merge 1 commit into
Conversation
MorningFrog
changed the title
MorningFrog
changed the title
MorningFrog
force-pushed
the
morningfrog-develop
branch
from
14f0e03 to
85c3579
Compare
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
This PR fixes the JAX SAC critic update logic reported in #425 .
Changes
critic_1andcritic_2critic_1's gradient only tocritic_1_optimizercritic_2's gradient only tocritic_2_optimizercritic_1_grad,critic_2_grad,policy_grad,entropy_gradfor clarity (this can be adjusted or reverted if maintainers prefer the previous naming style)Expected impact
Closes #425