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 my opinion, the following are missing or unclear points for the "comprehensive example" at page 84:
1-Initial policy ($\pi_0$) is not known because nothing is mentioned for this.
2-How can you define short episodes (such as episodes with length 1, 2) for states far-way from the terminal state (the blue one)? In this case, since you cannot reach terminal state after a few steps for far states, it is not clear how an episode is formed.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
In my opinion, the following are missing or unclear points for the "comprehensive example" at page 84:
1-Initial policy ($\pi_0$ ) is not known because nothing is mentioned for this.
2-How can you define short episodes (such as episodes with length 1, 2) for states far-way from the terminal state (the blue one)? In this case, since you cannot reach terminal state after a few steps for far states, it is not clear how an episode is formed.
Beta Was this translation helpful? Give feedback.
All reactions