search

pranz24 / pytorch-soft-actor-critic

PyTorch implementation of soft actor critic
MIT License
822 stars 182 forks source link

About model.py line 105 #17

Closed BangLiu closed 5 years ago

BangLiu commented 5 years ago

In model line 105, isn't the third return value should be:

torch.tanh(mean) * self.action_scale + self.action_bias

?

pranz24 commented 5 years ago

Yes Although @ku2482 will know better than me.

toshikwa commented 5 years ago

@BangLiu Yes, sorry for my easy mistake @pranz24 .

pranz24 commented 5 years ago

Awesome I'll fix it