Optimal policy - Numerical Example 0/2 points (graded) Recall that in this setup, the agent receives a reward (or penalty) of for every action that it takes, on top of the and when it reached the corresponding cells. Since the agent always starts at the state , and the outcome of each action is deterministic, the discounted reward depends only on the action sequences and can be written as: where the sum is until the agent stops. For the cases and , what is the maximum discounted reward that the agent can accumulate by starting at the bottom right corner and taking actions until it reached the top right corner