•   This plot shows the performance of learning algorithm for 1 serve over 1,000 trials
•   Here weights have been dumped and loaded in the successive run to tune the net
•   The number of iterations here are 3
•   The blue and pink lines are the final curves in the 3rd iteration.
•   The red and green lines are in the first iteration
•   Plota  where
•    a=1 refers to successful shots => reaching the ball
•    a=2 refers to completely successful shots => hitting a correct shot as well
• Here
•     Gamma = 0.9
•      Lambda = 0.95
•      Reward Function  = 2  for complete success

                                                                  = 1  for partial success
                                                                  = -1 for failure
                                                                  = 0 otherwise