What do we need to do this operation for computing image embedding in AC?

[raymondchua]

Hi, I have some trouble trying to understand why we need to do this in the ACModel:

https://github.com/lcswillems/rl-starter-files/blob/317da04a9a6fb26506bbd7f6c7c7e10fc0de86e0/model.py#L38

Can someone explain? I understand that 64 could be the number of output channel from the previous layer. But why do we need to do ((n-1)//2-2)?

Best, Raymond