[bugfix] continuous action precision mismatch#584
Merged
jsuarez5341 merged 1 commit intoJun 15, 2026
Conversation
yacineMTB
commented
Jun 13, 2026
yacineMTB
force-pushed
the
fix-continuous-action-logprob-4.0
branch
from
4dd4990 to
af45050
Compare
yacineMTB
force-pushed
the
fix-continuous-action-logprob-4.0
branch
from
af45050 to
21c987b
Compare
yacineMTB
changed the title
yacineMTB
changed the title
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
I think the best test that shows this improvement is an independent sweep before the fix, and then after the fix.
Basically; if precision_t was bf16/fp16, the sampled fp32 action gets rounded, and that messes with things downstream in PPO. I'm not sure exactly how PPO uses the ratio; but before this fix, if you did not change the policy, the logratio would be nonzero. As I understand it; if the policy did not change, this should be zero. With discrete actionspace, it does stay zero, but in continuous. it is does not.
discrete doesn't have this problem because it uses integers.