Question: 2. Problem 2 (It! pts). Consider two Markov Decision Processes, M1 and Mg, with corresponding reward functions R1 and R3. Suppose M1 and M2 are

2. Problem 2 (It! pts). Consider two Markov Decision Processes, M1 and Mg, with corresponding reward functions R1 and R3. Suppose M1 and M2 are identical except that the rewards for H2 are shifted by a constant from the rewards for R1: i.e., for all states a, 1115(3) 2 191(3) + c, where c does not depend upon 3. Prove that the optimal policy must he the same for both Markov Decision Processes
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
