[RLlib] Make the KL coefficient traced in appo tf #34293
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
Signed-off-by: Avnish <[email protected]>
avnishn
requested review from
sven1977,
gjoliver,
ArturNiederfahrenhorst,
smorad,
maxpumperla,
kouroshHakha and
krfricke
as code owners
kouroshHakha
approved these changes
Apr 12, 2023
Signed-off-by: Avnish <[email protected]>
…_appo_kl_coeff_traced
vitsai
pushed a commit
to vitsai/ray
that referenced
this pull request
Apr 17, 2023
Signed-off-by: Avnish <[email protected]>
elliottower
pushed a commit
to elliottower/ray
that referenced
this pull request
Apr 22, 2023
Signed-off-by: Avnish <[email protected]> Signed-off-by: elliottower <[email protected]>
ProjectsByJackHe
pushed a commit
to ProjectsByJackHe/ray
that referenced
this pull request
May 4, 2023
Signed-off-by: Avnish <[email protected]> Signed-off-by: Jack He <[email protected]>
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Outdated suggestions cannot be applied.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.
Signed-off-by: Avnish [email protected]
previously, if the appo learner update was traced with tf.function, then the kl coefficient wouldn't be automatically be update because python side affects aren't allowed inside of tf.function traced functions.
This pr makes the kl coefficient a tf variable and then updates it in the loop. It also adds a test to check if the kl coefficient changed after training.
Why are these changes needed?
Related issue number
Checks
git commit -s) in this PR.scripts/format.shto lint the changes in this PR.method in Tune, I've added it in
doc/source/tune/api/under thecorresponding
.rstfile.