A Further Investigation of Neural Network Players for Game 2048
A Further Investigation of Neural Network Players for Game 2048
复制标题
游戏 2048 神经网络玩家的进一步研究
DOI：
10.1007/978-3-030-65883-0_5
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Kiminori Matsuzaki
中科院分区：
文献类型：
--
作者：
Kiminori Matsuzaki
游戏2048是一个随机单人游戏。游戏2048的强大计算机玩家的开发基于通过强化学习训练的N元组网络。一些计算机播放器是用神经网络开发的，但它们的性能很差。在我们之前的工作中，我们证明了我们可以通过监督学习来开发更好的策略网络参与者。在这项研究中，我们进一步研究了游戏2048的神经网络玩家在两个方面。首先，我们关注组件（即，层），并在类似的设置中实现更好的性能。其次，我们改变网络的输入和/或输出以获得更好的性能。最好的神经网络播放器达到平均得分215 803没有搜索技术，这是相当的N元组网络播放器。
Game 2048 is a stochastic single-player game. Development of strong computer players for Game 2048 has been based on N-tuple networks trained by reinforcement learning. Some computer players were developed with neural networks, but their performance was poor. In our previous work, we showed that we can develop better policy-network players by supervised learning. In this study, we further investigate neural-network players for Game 2048 in two aspects. Firstly, we focus on the component (i.e., layers) of the networks and achieve better performance in a similar setting. Secondly, we change input and/or output of the networks for better performance. The best neural-network player achieved average score 215 803 without search techniques, which is comparable to N-tuple-network players.