Neuroscientists postulate 3D representations in the brain in a variety of different coordinate frames (e.g. 'head-centred', 'hand-centred' and 'world-based'). Recent advances in reinforcement learning demonstrate a quite different approach that may provide a more promising model for biological representations underlying spatial perception and navigation. In this paper, we focus on reinforcement learning methods that reward an agent for arriving at a target image without any attempt to build up a 3D 'map'. We test the ability of this type of representation to support geometrically consistent spatial tasks such as interpolating between learned locations using decoding of feature vectors. We introduce a hand-crafted representation that has, by design, a high degree of geometric consistency and demonstrate that, in this case, information about the persistence of features as the camera translates (e.g. distant features persist) can improve performance on the geometric tasks. These examples avoid Cartesian (in this case, 2D) representations of space. Non-Cartesian, learned representations provide an important stimulus in neuroscience to the search for alternatives to a 'cognitive map'.

中文翻译：

---

强化学习空间生物表征的经验教训。

神经科学家假设大脑中的 3D 表示在各种不同的坐标系中（例如“以头部为中心”、“以手为中心”和“基于世界”）。强化学习的最新进展展示了一种完全不同的方法，它可以为空间感知和导航的生物表征提供更有前景的模型。在本文中，我们专注于强化学习方法，该方法奖励代理到达目标图像，而无需尝试构建 3D“地图”。我们测试了这种表示支持几何一致空间任务的能力，例如使用特征向量解码在学习位置之间进行插值。我们引入了一种手工制作的表示，其设计具有高度的几何一致性，并证明，在这种情况下，有关相机平移时特征持久性的信息（例如远处特征持久性）可以提高几何任务的性能。这些示例避免了空间的笛卡尔（在本例中为 2D）表示。非笛卡尔的学习表征为神经科学中寻找“认知地图”的替代方案提供了重要的刺激。