If we select the top-left state and the action 'right', what is the value of Q[top-left,right] using asynchronous value iteration?
  • Q[top-left,right] = 0.8(-100 + 0.9(1)) + 0.1(-100 + 0.9(-1)) + 0.1(0 + 0.9(-10)) = -90.27

Valid HTML 4.0 Transitional