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
The False case applies only to meta-gradients use case which is rare in the common agents. We should mark this option as defaulted to be True to avoid usage bugs.
WDYT?
The text was updated successfully, but these errors were encountered:
truncated_generalized_advantage_estimation
should have thestop_target_gradients
defaulted toTrue
https://github.com/deepmind/rlax/blob/383f93bc8b33c3d1bc28f15e1e07fc5104c790ea/rlax/_src/multistep.py#L279
The
False
case applies only to meta-gradients use case which is rare in the common agents. We should mark this option as defaulted to beTrue
to avoid usage bugs.WDYT?
The text was updated successfully, but these errors were encountered: