To train our model, we will use a list of board positions followed by the best optimal response for a number of different boards. We can reduce the amount of boards to train on by considering only board positions that are different with regard to symmetry. The non-identity transformations of a Tic Tac Toe board are a rotation (in either direction) of 90 degrees, 180 degrees, and 270 degrees, a horizontal reflection, and a vertical reflection. Given this idea, we will use a shortlist of boards with the optimal move, apply two random transformations, and then feed that into out neural network for learning.
Since Tic Tac Toe is a deterministic game, it is worth noting that whoever goes first should either win or draw. We will hope ...
