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 dra...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | Ukrainian |
| Published: |
Igor Sikorsky Kyiv Polytechnic Institute
2022-10-01
|
| Series: | Sistemnì Doslìdženâ ta Informacìjnì Tehnologìï |
| Subjects: | |
| Online Access: | http://journal.iasa.kpi.ua/article/view/269583 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|