Multi-step prediction in linearized latent state spaces for representation learning
Andrii Tytarenko • Sistemnì Doslìdženâ ta Informacìjnì Tehnologìï
(2022)
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 cur...
DOAJ
Open Access (DOAJ)
DOI:
10.20535/SRIT.2308-8893.2022.3.09