test(ddpg): add actor Q-improvement trend coverage (update_actor) - #125
Open
belarusian wants to merge 1 commit into
Open
test(ddpg): add actor Q-improvement trend coverage (update_actor)#125belarusian wants to merge 1 commit into
belarusian wants to merge 1 commit into
Conversation
TICKET-055 / issue #124: the actor side was only ever checked for finiteness. Add test_actor_q_improves_over_updates, which runs repeated update_actor steps on a fixed batch and asserts the actor's mean Q-value (the quantity update_actor maximises) strictly improves and the actor loss (-mean Q) falls. Measured +0.0117 for seed=42, deterministic and positive across seeds 0/1/7/42.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
TICKET-055 / issue #124: the actor side of DDPG was only ever checked for finiteness. Adds test_actor_q_improves_over_updates, which runs repeated update_actor steps on a fixed batch and asserts the actor's mean Q-value (the quantity update_actor maximises) strictly improves and the actor loss (-mean Q) falls. Measured +0.0117 for seed=42, deterministic and positive across seeds 0/1/7/42.
Gate: pytest tests/ -q (POLYGON_API_KEY=dummy) RC=0 (611 collected = 610 + 1 new); ruff check alloc/ clean; mypy alloc/ --ignore-missing-imports clean (20 files).
Closes #124