论文标题
表示表示学习的线性潜在状态空间中的多步预测
Multi-Step Prediction in Linearized Latent State Spaces for Representation Learning
论文作者
论文摘要
在本文中，我们得出了一种新的方法作为对LCE（例如E2C）的概括。该方法通过添加多步预测来开发学习局部线性状态空间的想法，从而可以对曲率进行更明确的控制。我们表明，该方法的表现优于E2C，而没有其他作品（例如PCC和P3C）随附的急剧模型。我们讨论了E2C和提出的方法与派生的更新方程之间的关系。我们提供经验证据，这表明，通过考虑多步预测，我们的方法MS -E2C-可以从曲率和下一个状态可预测性方面学习更好的潜在状态空间。最后，我们还讨论了我们遇到的某些稳定挑战，以及减轻它们的方法。
In this paper, we derive a novel method as a generalization over LCEs such as E2C. The method develops the idea of learning a locally linear state space, by adding a multi-step prediction, thus allowing for more explicit control over the curvature. We show, that the method outperforms E2C without drastic model changes which come with other works, such as PCC and P3C. We discuss the relation between E2C and the presented method and derived update equations. We provide empirical evidence, which suggests that by considering the multi-step prediction our method - ms-E2C - allows to learn much better latent state spaces in terms of curvature and next state predictability. Finally, we also discuss certain stability challenges we encounter with multi-step predictions and the ways to mitigate them.
