fix(sac): discount entropy backup in target - #110
Open
zjn20030811 wants to merge 1 commit into
Open
Conversation
Apply the entropy backup inside the discounted, terminal-masked next-state value and cover both entropy and non-entropy targets with deterministic tests. Fixes rail-berkeley#93
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
When backup_entropy is enabled, critic_loss_fn currently subtracts temperature*log_prob after bootstrapping, so terminal transitions receive an entropy correction and the correction is not discounted. This change builds the next-state value first and applies the discount and mask to both Q and entropy terms, with focused regression tests for terminal and non-terminal targets. Tests: pytest serl_launcher/tests/test_sac.py -q (2 passed). Fixes #93