Is it safe to have two normalization ranges for observations?

Can I have some observations to be within the range (0f, 1f) and others to be within the range (-1f, 1f)? Will it make training worse?

depends. If you have positions and you scale them differently although length (e.g. one meter) should be the same, ML has to figure out the mapping. I would recommend scaling same things with the same factor. So transform.position/maxCoordinate.
If you scale two independent things differently it should not matter.

I personally use normalize=true bc it is the safest way

1 Like