fix: compare jaxmarl space bounds and cardinalities - #1221
Open
quinnarnold wants to merge 1 commit into
Open
quinnarnold wants to merge 1 commit into
quinnarnold wants to merge 1 commit into
Conversation
quinnarnold
requested review from
OmaymaMahjoub,
RuanJohn,
SimonDuToit,
WiemKhlifi and
sash-a
as code owners
September 22, 2026 17:40
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What?
Fixes #961. Compare the observation and action spaces of JaxMARL agents beyond their shapes.
Why?
Equal-shaped spaces can have different discrete action counts, bounds, or dtypes. The shape-only check accepts these as homogeneous.
How?
Compare shape and dtype, then discrete cardinality or Box bounds, using the existing Gymnax/JaxMARL type helpers. Reduce array-valued bound comparisons to a boolean.
Extra
Local validation passed 40 observation/action comparisons and a real SimpleSpread JIT reset/step. The original implementation fails the unequal-cardinality check. These checks were run separately; no repository test files were changed.
Applicable pre-commit hooks pass except mypy, which reports the same pre-existing
HiddenStatestype error atmava/systems/gpo/anakin/rec_magpo.py:664on a clean archive of the upstream base.AI assistance.