Multi-Step Prediction in Linearized Latent State Spaces for Representation Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Representation LearningSimilar Papers 제목 키워드 기반
Semantic Communication and Control Co-Design for Multi-Objective Correlated Dynamics
This letter introduces a machine-learning approach to learning the semantic dynamics of correlated systems with different control rules and dynamics. By leveraging the Koopman operator in an autoencoder (AE) framework, t…
Semantic CommunicationSparsifying dimensionality reduction of PDE solution data with Bregman learning
Classical model reduction techniques project the governing equations onto a linear subspace of the original state space. More recent data-driven techniques use neural networks to enable nonlinear projections. Whilst thos…
compressed sensingDecoderDimensionality ReductionEfficient Dynamics Modeling in Interactive Environments with Koopman Theory
The accurate modeling of dynamics in interactive environments is critical for successful long-range prediction. Such a capability could advance Reinforcement Learning (RL) and Planning algorithms, but achieving it is cha…
Reinforcement Learning (RL)Instance-Level Post Hoc Uncertainty Quantification in Object Detection
Object detection is a safety-critical component of autonomous driving. It is essential to quantify the uncertainty in bounding-box predictions for safety assurance. Post hoc uncertainty quantification without retraining …
Autonomous DrivingObject DetectionHierarchical Latent Prediction for Language Models
While standard Next-Token Prediction (NTP) lays the foundation of language model pre- training, its teacher-forced training paradigm may not be optimal for long-horizon reasoning and planning. Recent works such as Multi-…