BriefGPT.xyz
Sep, 2022
线性化潜在状态空间中的多步预测用于表示学习
Multi-Step Prediction in Linearized Latent State Spaces for Representation Learning
HTML
PDF
A. Tytarenko
TL;DR
本文提出了一种新的方法，通过添加多步预测来学习本地线性状态空间，从而允许更明确地控制曲率，并通过实证证据表明，该方法可允许学习更好的潜在状态空间。
Abstract
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
→