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
Hi, I was just trying to understand the architecture of the OneStepModel. During prediction it passes the action into every layer together with the output from the previous one. Where does this architecture come from? Why does it work better than just passing the actions into the first state? I would be very thankful if you could let me know where this comes from the help my understanding :)
The text was updated successfully, but these errors were encountered:
Hi, I was just trying to understand the architecture of the
OneStepModel
. During prediction it passes the action into every layer together with the output from the previous one. Where does this architecture come from? Why does it work better than just passing the actions into the first state? I would be very thankful if you could let me know where this comes from the help my understanding :)The text was updated successfully, but these errors were encountered: