13. Exercise 4: Solution

Solution

T=0

  • State = [176.62, 174.37, 215040582]
  • Action = Buy
  • Next State = [177.79, 174.744, 27864737]
  • Reward = 0

T=1

  • State = [177.79, 174.744, 27864737]
  • Action = Sell 
  • Next State = [175.16, 175.1165, 209132299]
  • Reward = 175.16 - 177.79 = -2.63

T=2

  • State = [175.16, 175.1165, 209132299]
  • Action = Buy
  • Next State = [176.79, 175.249, 18063555]
  • Reward = 0

T=3

  • State = [176.79, 175.249, 18063555]
  • Action = Hold
  • Next State = [177.24, 175.3795, 19618497]
  • Reward = 0

T=4

  • State =  [177.24, 175.3795, 19618497]
  • Action = Sell
  • Next State = [175.09, 175.4385, 21869857]
  • Reward = 175.09 - 176.79 = -1.7

T=5

  • State =  [175.09, 175.4385, 21869857]
  • Action = Buy
  • Next State = [176.3, 175.347, 20160085]
  • Reward = 0

T=6

  • State = [176.3, 175.347, 20160085]
  • Action = Sell
  • Next State = [179.63, 175.2695, 58582743]
  • Reward = 179.63 - 176.3 = +3.33