You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have been reading this code and I saw in line 177 of train.py, rewards[:-1] is used instead of rewards[1:] for reward_loss. Is that a bug? If not, could you please explain why rewards[:-1] is correct?
Thank you
The text was updated successfully, but these errors were encountered:
I have been reading this code and I saw in
line 177
of train.py, rewards[:-1] is used instead of rewards[1:] for reward_loss. Is that a bug? If not, could you please explain why rewards[:-1] is correct?Thank you
The text was updated successfully, but these errors were encountered: