[RLlib] why is TF value out initialization 100x smaller than torch?

Hey does anyone know why the value_out std initialization in tf/fcnet.py is 0.01 while the torch std initialization in torch/fcnet.py is 1.0?

Great question @raoul-khour-ts ! There is no good reason to have these defaults for tf and torch be different. We should fix this. …

@sven1977 If there is a reason to chage initializer maybe the better option will be changing to Xavier Glorot initializer as default ?

Also a good point (for CNNs, that’s what we already use). The thing is, I don’t want to change the default w/o having at least run some benchmarks again.
I did change torch’s vf layer to 0.01 (normc), just like tf’s fcnet works. The risk of that should be relatively low: