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
In obj_alpha = (self.alpha_log * (self.target_entropy - log_prob).detach()).mean() when alpha_log=0, alpha will be 1forever.
the correct way is obj_alpha = (self.alpha * (self.target_entropy - log_prob).detach()).mean() .
In
obj_alpha = (self.alpha_log * (self.target_entropy - log_prob).detach()).mean()
when alpha_log=0, alpha will be 1forever.the correct way is
obj_alpha = (self.alpha * (self.target_entropy - log_prob).detach()).mean()
.this problem is also found in rlkit.
Algorithm details in the source code of :
https://github.com/rail-berkeley/softlearning/blob/13cf187cc93d90f7c217ea2845067491c3c65464/softlearning/algorithms/sac.py#L256
The text was updated successfully, but these errors were encountered: