.png){kind=icon}
.png){kind=icon}
Return
Using CNN for solving two-player zero-sum games
.png){kind=icon}
OA
AI
DOI：10.1016/j.eswa.2022.117545.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We study a two-player zero-sum game (matrix game for short) with the objective of finding the saddle point and its value. We develop a novel convolutional neural network (CNN for short) approach to achieve the goal. We propose a complete training pipeline, including a specific CN N model structu r e to handle varying game sizes, generating training datasets, and model fitting. The experiment results show that ou r proposed method outperforms the traditional linear programming (LP for short) method and two regret minimization learning algorithms in terms of computational efforts.
Keywords:
Two-player zero-sum game
Saddle point
Convolutional neural network
Machine learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W