[RLlib] Add off-policy'ness metric to new API stack. #48227
Merged
+72
−58
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
…off_policyness_metric_to_new_api_stack
sven1977
added
tests-ok
simonsays1980
approved these changes
Oct 24, 2024
| @@ -98,21 +98,6 @@ | |||
| LR_KEY = "learning_rate" | |||
|
|
|||
|
|
|||
| @dataclass | |||
There was a problem hiding this comment.
Finally this thing is gone :)
Jay-ju
pushed a commit
to Jay-ju/ray
that referenced
this pull request
Nov 5, 2024
JP-sDEV
pushed a commit
to JP-sDEV/ray
that referenced
this pull request
Nov 14, 2024
Signed-off-by: JP-sDEV <jon.pablo80@gmail.com>
mohitjain2504
pushed a commit
to mohitjain2504/ray
that referenced
this pull request
Nov 15, 2024
Signed-off-by: mohitjain2504 <mohit.jain@dream11.com>
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Outdated suggestions cannot be applied.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.
Add off-policy'ness metric to new API stack.
The old stack has a convenient metric measuring how many policy updates the sampling/behavior policy is behind the actually trained one. For algorithms like APPO and IMPALA, this metrics is crucial for understanding learning deficiencies and its values should be as close to 1 as possible (1 update behind).
The metric can be found in the result dict under (analogous to the old API stack's metric):
learners/[module_id]/diff_num_grad_updates_vs_sampler_policy
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.