ikostrikov/pytorch-a2c-ppo-acktr-gail

Operations that have no effect

Opened this issue · 0 comments

Hi,
The two lines referenced below seem to have canceling effects (the second quoted line is the inverse of the sigmoid). I was wondering what has been the purpose of putting them.

s = torch.sigmoid(d)
reward = s.log() - (1 - s).log()

I think if the purpose has been to make this a Wasserstein GAIL, it would be nice to do sth like
if args.wasserstein... else...