•               This plot shows the performance of learning algorithm for 1 serve over 10,000 trials
•                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