Systematic Selection of N-Tuples for Game 2048 Using Neural-Network Function Approximator
摘要
N-tuple networks are simple and efficient methods for generating evaluation functions and have been used with an increasing number of N-tuples to develop state-of-the-art 2048 computer players. Although performance is expected to improve as the number of N-tuples increases, a systematic method is needed to find a good combination of many N-tuples. In this study, we propose the third systematic method that can be applied to any number of N-tuples and take into account the interdependency between them. Our approach has two main steps: first, we formulate the problem with a function from a combination of N-tuples to an evaluation value; second, we use neural networks to approximate this function. We compare the combinations selected by existing methods and proposed methods as well as those designed manually. Although the combinations selected by the proposed method did not outperform those from our previous work, they achieved better results than the manually designed combinations.