论文标题
有限的小组模棱两可的神经网络
Finite Group Equivariant Neural Networks for Games
论文作者
论文摘要
诸如GO，国际象棋和跳棋之类的游戏具有多个等效的游戏状态，即应该做对称和相反动作的多个董事会位置。这些等效性并非被当前的艺术神经药物的当前状态所利用，而这些神经药物必须重新学习相似的信息，从而浪费计算时间。现有工作中的小组epovariant CNN创建网络，可以利用对称性来改善学习，但是，它们缺乏正确反映游戏所需的移动嵌入的表现力。我们介绍了有限的组神经网络（FGNNS），这是一种创建对这些董事会职位的天生理解的代理的方法。证明FGNN可以提高网络播放检查器（草稿）的性能，并且很容易适应其他游戏和学习问题。此外，可以从现有网络体系结构创建FGNN。这些首次包括具有跳过连接和任意层类型的人。我们证明，u-net（FGNN-U-net）的均等版本优于图像分割中未修改的网络。
Games such as go, chess and checkers have multiple equivalent game states, i.e. multiple board positions where symmetrical and opposite moves should be made. These equivalences are not exploited by current state of the art neural agents which instead must relearn similar information, thereby wasting computing time. Group equivariant CNNs in existing work create networks which can exploit symmetries to improve learning, however, they lack the expressiveness to correctly reflect the move embeddings necessary for games. We introduce Finite Group Neural Networks (FGNNs), a method for creating agents with an innate understanding of these board positions. FGNNs are shown to improve the performance of networks playing checkers (draughts), and can be easily adapted to other games and learning problems. Additionally, FGNNs can be created from existing network architectures. These include, for the first time, those with skip connections and arbitrary layer types. We demonstrate that an equivariant version of U-Net (FGNN-U-Net) outperforms the unmodified network in image segmentation.
