0
$\begingroup$

What does the term "expected leaf node" in the Exercise below from Sutton-Barto mean?

enter image description here

$\endgroup$
1
  • $\begingroup$ Since the state value of the root is an expectation w.r.t. a policy, thus it expects leaf nodes as all its possible action values explicitly without respect to the said policy as you already understood. Do you still have questions, if not, you can close or remove this one. $\endgroup$
    – cinch
    Commented Feb 16 at 19:51

0

You must log in to answer this question.