Mathematics

Bentley Braun

27 February, 17:38

The initial policy is π (A) = 1 and π (B) = 1. That means that action 1 is taken when in state A, and the same action is taken when in state B as well. Calculate the values V π 2 (A) and V π 2 (B) from two iterations of policy evaluation (Bellman equation) after initializing both V π 0 (A) and V π 0 (B) to 0.