[RLlib] Fit ES and ARS results dict to rest of RLlib, enable results to be fetched in release tests and and CI learning tests #35588
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
…to be fetched in release tests and and CI learning tests (ray-project#35533) Signed-off-by: Artur Niederfahrenhorst <attaismyname@googlemail.com>
ArturNiederfahrenhorst
requested review from
sven1977,
gjoliver,
avnishn,
smorad,
maxpumperla,
kouroshHakha and
krfricke
as code owners
zhe-thoughts
approved these changes
May 22, 2023
Signed-off-by: Artur Niederfahrenhorst <attaismyname@googlemail.com>
zhe-thoughts
approved these changes
May 22, 2023
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Outdated suggestions cannot be applied.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.
Why are these changes needed?
At the moment, ES humanoid release test does not pass even though rewards are high enough.
This is because we don't make use of our usual metrics construction in ES.
This PR makes it so that ES returns the reward from evaluation workers like other algorithms do.
This is needed because our test utils that are used for release tests expect the mean reward to be at the same place for all algorithms.
Picks #35533