•        This plot shows the performance of learning algorithm for 1 serve over 20,000 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 = 10  for complete success
                                               = 5 for partial success
                                               =  -1 for failure
                                                = 0 otherwise