Include a cold start bandit test case #71
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
aarsilv
commented
Nov 7, 2024
ufc/bandit-flags-v1.json
Outdated
| @@ -227,6 +227,31 @@ | |||
| } | |||
| ], | |||
| "totalShards": 10000 | |||
| }, | |||
| "cold_start_bandit": { | |||
There was a problem hiding this comment.
Flag in the UFC so that we can request an assignment from the cold-started bandit
| @@ -0,0 +1,81 @@ | |||
| { | |||
| "flag": "cold_start_bandit_flag", | |||
There was a problem hiding this comment.
The new test case! We check all three variations
| @@ -286,7 +311,7 @@ | |||
| "variationValue": "banner_bandit" | |||
| } | |||
| ], | |||
| "modelVersion": "v123" | |||
| "modelVersion": "123" | |||
There was a problem hiding this comment.
Removing the v to mirror the production change we're making. It doesn't make a material difference as long as this is consistent with bandit-models-v1.json
typotter
approved these changes
Nov 7, 2024
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Outdated suggestions cannot be applied.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.
We want to test when a bandit has cold-started, e.g., no model parameters have been generated yet.
Note that the UFC is currently inconsistent with the name of the version of a cold-started bandit, with "
cold start" used in the model parameters andnullused in the UFC. We need to align on one to avoid errors.The plan is to align on committing the
vprefix and using the"cold start"placeholder as this is more SDK friendly.See all passing with
cold startas the model version: https://github.com/Eppo-exp/sdk-test-data/actions/runs/11715905905/job/32633092353?pr=71Mixed Results when
nullis the model version: https://github.com/Eppo-exp/sdk-test-data/actions/runs/11715993935/job/32633330226?pr=71This PR updates the test data to match that plan.