How to Make a Better Move in a Dice Roll

Tisaro used reinforcement learning to teach t d gammon how to play backgammon. He had the peter play itself millions of times, over and over and over again. Every time it won a game, it would saye what moves did i make thit allow me to win the game? And it would assign positive values to those moves. But every time it lost a game, It would assign negative values to the moves that it mane.