search

nnaisense / evotorch

Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.
https://evotorch.ai
Apache License 2.0
997 stars 62 forks source link

Fix CMAES._get_sigma #103

Closed famura closed 3 months ago

famura commented 5 months ago

See issue #101

Do not cast sigma to a builtin float but keep it as a torch.Tensor. Now the return type also matches with the superclass.

flukeskywalker commented 5 months ago

@NaturalGradient what do you think?

flukeskywalker commented 3 months ago

We forgot to close this, but having discussed it, @engintoklu and I had decided that sigma should remain a float. As noted by @NaturalGradient above, in the context of CMA-ES, sigma is not a variable that can be specified for each dimension (which can be true in the context of other distribution-based algorithms). Unfortunately the similar naming across algorithms may cause confusion.

Nevertheless, we appreciate you bringing this to our attention @famura!