I just noticed that the code is using TruncNormal as the actor distribution instead of TanhNormal as in v1. I wonder did you make some ablations on these two choices and see TruncNormal provide better results? Or the change is only because the entropy of TruncNormal is easier to compute than TanhNormal for the entropy regularizer?
Hey @danijar.
I just noticed that the code is using
TruncNormalas the actor distribution instead ofTanhNormalas in v1. I wonder did you make some ablations on these two choices and seeTruncNormalprovide better results? Or the change is only because the entropy ofTruncNormalis easier to compute thanTanhNormalfor the entropy regularizer?