reward $=$ function$($policy$,$ MDP$)\{$

$$ rew $=0$

$$ state $=1$

$$ for$($i in $1$:$10)\{$

$$ if$($state $==9)\{$

$$ break

$\}$

#$$ MDP$\_$AB$,$ MDP$\_$AC$,$ MDP$\_$BC$,$ MDP$\_$BA$,$ MDP$\_$CA$,$ MDP$\_$CB

p$\_$mdp$=$c$(1/3,1/4,1/12,1/6,1/12,1/12)$

# Here are the assignment MDPs

assignments$=$list$($MDP$\_$AB$,$ MDP$\_$AC$,$ MDP$\_$BC$,$ MDP$\_$BA$,$ MDP$\_$CA$,$ MDP$\_$CB$)$

# Here are the labels for each assignment

assigns$=$c$(\text{'}$MDP$\_$AB$\text{'},\text{'}$MDP$\_$AC$\text{'},\text{'}$MDP$\_$BC$\text{'},\text{'}$MDP$\_$BA$\text{'},\text{'}$MDP$\_$CA$\text{'},\text{'}$MDP$\_$CB$\text{'})$

# For each assignment's best policy

for$($pi in $1$:length$($assignments$))\{$

$$ # Find the optimal policy

$$ pol $=$ # YOUR CODE HERE

$$ # Create a variable to store the expected reward

$$ er $=0$

$$ # For each assignment

$$ for$($mdp in $1$:length$($assignments$))\{$

$$

$$ # Calculate the reward R$($pi$,$ MDP$)$

$$ r $=$ YOUR CODE HERE

$$ # Update the expected rewards E$[$R$($pi$,$ MDP$)]$

$$ er $=$ # YOUR CODE HERE

$\}$

$$ message$($assigns$[$pi$],\text{'}\text{'},$ er$)$

$\}$ Complete the three code snippets $($your answer here$)$