$1$

CSC $465/665$ Artificial Intelligence Fall $2023$

Suppose that we have the following observed transitions: $($B$,$ East, C$,2),($C$,$ South, E$,6),($C$,$

East, D$,5),($C$,$ North, A$,4)$ The initial value of each state is $0.$ Assume that $=1$ and $=$

$0\mathrm{.}5.$

What are the learned values from TD learning after all four observations?

What are the learned Q$-$values from Q$-$learning after all four observations?