2. (6 points) Direct Policy Evaluation: You observed the following episodes from an undiscounted MDP with two states A and B as below (the numbers denote the reward you receive): (A,+2) + (A, +1) +(B,-2) + (A, +2) + (B,-1) + terminate (B,-2) + (A, +2)(B, -1) + terminate Estimate the value function using direct evaluation (do not use Bellman Equations) and fill in the table below. Make sure to show your work below the table. V(A) V(B)