In this post we report success in using reinforcement to learn the game of nim. We had previously cited two theses (ERIK JÄRLEBERG (2011) and PAUL GRAHAM & WILLIAM LORD (2015)) that used Q-learning to learn the game of nim. However, in this setting, the scaling issues with Q-learning are much more severe than with value-learning. In this post we use a value-based approach with a table. Because the value-based approach is much more efficient than Q-learning no functional approximation is needed, up to reasonable heap sizes.