In this homework you will experiment with reinforcement learning. The directory ~echown/courses/370/chess contains files pieces.cc and pieces.hh which will learn to play an end-game in chess with no prior knowledge of the game. The end-game for the homework is one in which one side has only a King left and the other side has a King and a Queen. The two possible results are a Draw (when the side with the King takes the Queen) and a win for the side with the Queen. The reinforcement learning system interacts with a chess system. It gets state information to update its Q function, and it gets the number of available moves in each state. It has no information whatsoever about chess. Your goal in this homework is to experiment with training regimes for the system in order to maximize performance along several dimensions. Ideally a good system should do at least the following things well: