SAC alpha update problem

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