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
loss2=-correction_coeff*pi*torch.log(pi) * (q.detach()-v) # bias correction term
According to original paper, gradient for bias correction term is define as below,
and as pi serves as the probability for expectation calculation, it seems it's not the target of optimization.
Shouldn't we detach the pi from computational graph at above line?
The text was updated successfully, but these errors were encountered:
minimalRL/acer.py
Line 104 in 46f9b32
According to original paper, gradient for bias correction term is define as below,
and as
pi
serves as the probability for expectation calculation, it seems it's not the target of optimization.Shouldn't we detach the
pi
from computational graph at above line?The text was updated successfully, but these errors were encountered: