Using CNN for solving two-player zero-sum games

We study a two-player zero-sum game (matrix for short) with the objective of finding saddle point and its value. develop novel convolutional neural network (CNN approach to achieve goal. propose complete training pipeline, including specific CNN model structure handle varying sizes, generating datasets, fitting. The experiment results show that our proposed method outperforms traditional linear programming (LP two regret minimization learning algorithms in terms computational efforts. • use solve games. Concrete are train Our can different sizes untrained generation distributions. shows great potential efficiency.