Finite Group Equivariant Neural Networks for Games
This work addresses inefficiencies in neural agents for games and image segmentation by incorporating symmetry understanding, but it is incremental as it builds on existing group equivariant CNNs.
The paper tackled the problem of neural agents not exploiting equivalent game states in games like go, chess, and checkers, leading to wasted computing time, and introduced Finite Group Neural Networks (FGNNs) to address this, showing improved performance in checkers and image segmentation with FGNN-U-Net outperforming the unmodified network.
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.