Artificial Intellegnce Question

0.59 0.67 0.77 0.57 0.6 0.60 0.780.66 0.85 1.00 0.67 5. (15 points) V(s), Q(s, a), 7(s) The Q-Values of a gridworld problem after many iterations are shown on the diagram 1,00 is the positive exit (escape from the gridworld), and -1.00 is the negative exit (death). 0.53 0.57 0.57 0.57 0.51 0.51 0.53 (-0.60 -1.00 0.86 0.89 0.30 0.88 0.00 -0.65 10.45 0.41 0.83 0.42 0.80 0.29 0.28 0.13 0.44 0.00 0.41 0.27 a) What are V-Values? Show them on a similar diagram with possible direction symbols. b) Write the policies that can be derived from the final V-Values. The agent will start from one of the bottom squares. c) Why is it better to use discounted utility when calculating rewards for an agent