Martin Schubert

Sorry, can you pare down your code to the bare minimum which exhibits the problem, and then paste it in a code block? See here for help: https://docs.github.com/en/get-started/writing-on-github/working-with-advanced-formatting/creating-and-highlighting-code-blocks

Can you please provide the full code that reproduces the problem? So that I can just copy and paste it in an empty notebook and reproduce the issue.

OK, the issue is that there are several parameters which define the geometry, and you are adjusting only some of them. I suggest taking a look at the `ceviche.defaults` module...

I think you need to implement your own version of this function: https://github.com/invrs-io/gym/blob/4758d3ae29bcc088b086bc8fb0f97dea2e4d1ab4/src/invrs_gym/challenges/ceviche/defaults.py#L184-L264

Please create a new issue if you have new questions.

Thanks for reporting this. It seems the Python version specified in the pyproject.toml is incorrect, since I am using some python 3.10 language features. I’ll make an update. Will it...

You should be able to design a diffractive supplier by replacing `challenges.metagrating()` with ` challenges.diffractive_splitter()`. Check the `challenges/__init__.py` for a consolidated view of all the challenge constructors (https://github.com/invrs-io/gym/blob/main/src/invrs_gym/challenges/__init__.py). FYI if...

Please create a new issue if you have additional questions.

It seems that jax 0.4.33 causes `test_fmm_anisotropic.py` to hang

It seems that these failures are flakey. See the following where repeated runs of the same test cause failures in some cases but not others. https://github.com/facebookresearch/fmmax/actions/runs/10967301414