Suppose you are provided with the following $4$ episodes of data from an RL problem

Episode $1$

A$,$ left, $C,1$

C$,$ left, D$,1$

D$,$ right, $T,0$

Episode $3$

A$,$ right, $B,1$

$B,$ right, $C,0$

C$,$ left, T$,0$

Episode $2$

B$,$ right, D$,1$

$D,$ right $T,0$

Episode $4$

B$,$ right, D$,1$

$D,$ left; $T,0$