Exercise 1 You are required to formulate the game Reversi as a reinforcement learning problem in a simple formulation. The formulation should be as precise as pos- sible. Below are conditions on the formulation. The objective is to win. It is better for the player to have more pieces in the final state of the board. The board is an 8x8 grid. You are also required to explain why the formulation represents the game Reversi and why it satisfies the conditions