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
{{ message }}
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
I'm reading the paper and code, and can't follow the truncation process. Table 2 sets exploration stddev. clip equal to 0.3, so I assume that the exploration noise is clipped. However, the action seems to be selected by action = dist.sample(clip=None) which does no clipping. Instead clipping is seemingly applied during training with dist.sample(clip=self.stddev_clip). Am I misunderstanding something here? Thanks!!
The text was updated successfully, but these errors were encountered:
I'm reading the paper and code, and can't follow the truncation process. Table 2 sets exploration stddev. clip equal to 0.3, so I assume that the exploration noise is clipped. However, the action seems to be selected by
action = dist.sample(clip=None)
which does no clipping. Instead clipping is seemingly applied during training withdist.sample(clip=self.stddev_clip)
. Am I misunderstanding something here? Thanks!!The text was updated successfully, but these errors were encountered: