Q$5$ Please use model free reinforcement learning to estimate the outputs for each state of A$,$ B$,$ C$,$ D and E

$\backslash$table$[[,$Observed Episodes $($Training$),,],[$Input Policy $,$Episode $1,$Episode $2],[,$A$,,$B$,$ east, C$,-2,$B$,$ east, C$,-1],[,,,$D$,$ exit, $x,+16,$D$,$ exit, $x,+16$