Question: Part 3 (21 points - each part 7 points) For the following problem, we add a new state in which we can take the EXIT


Part 3 (21 points - each part 7 points) For the following problem, we add a new state in which we can take the EXIT action with a reward of +x. b) For what values of x does value iteration take the minimum number of a) For what values of x is it guaranteed that our optimal policy has iterations k to converge to V for all states? Write and if there is no (C)= ? Write and if there is no upper or lower bound, upper or lower bound, respectively. Write the upper and lower bounds respectively. Write the upper and lower bounds in each respective in each respective box. If there is no values that we can consider for x to box. If there is no values that we can consider for x to guarantee the guarantee the condition mentioned above, explain that. For any values, condition mentioned above, explain it. For any values, explain your explain your answer. answer. c) What is the minimum number of iterations k until V H has converged to V for all states? Explain your
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
