Consider the well-known game of rock-paper-scissors. Human players often try to use the history of previous moves to guess the next move. Would you use a Q-learning or a policy-based method to learn...

Consider the well-known game of rock-paper-scissors. Human players often try to use the history of previous moves to guess the next move. Would you use a Q-learning or a policy-based method to learn to play this game? Why? Now consider a situation in which a human player samples one of the three moves with a probability that is an unknown function of the history of 10 previous moves of each side. Propose a deep learning method that is designed to play with such an opponent. Would a well-designed deep learning method have an advantage over this human player? What policy should a human player use to ensure probabilistic parity with a deep learning opponent?