论文标题
马里奥（Mario
Mario Plays on a Manifold: Generating Functional Content in Latent Space through Differential Geometry
论文作者
论文摘要
深层生成模型可以自动创建不同类型的内容。但是，不能保证这种内容将满足将其呈现给最终用户并具有功能的标准，例如生成的水平可能是无法解决的或不连贯的。在本文中，我们从几何学角度研究了这个问题，并为基于Riemannian几何形状的分类VAE的潜在空间提供了可靠的插值和随机步行的方法。我们用“超级马里奥兄弟”和“ Zelda的传奇”水平测试我们的方法，以及受到当前实践启发的更简单基线的测试。结果表明，我们提出的几何形状可以更好地插入和样品，可靠地靠近解码为可玩内容的潜在空间的部分。
Deep generative models can automatically create content of diverse types. However, there are no guarantees that such content will satisfy the criteria necessary to present it to end-users and be functional, e.g. the generated levels could be unsolvable or incoherent. In this paper we study this problem from a geometric perspective, and provide a method for reliable interpolation and random walks in the latent spaces of Categorical VAEs based on Riemannian geometry. We test our method with "Super Mario Bros" and "The Legend of Zelda" levels, and against simpler baselines inspired by current practice. Results show that the geometry we propose is better able to interpolate and sample, reliably staying closer to parts of the latent space that decode to playable content.
