Header logo is am

Probabilistic Recurrent State-Space Models




State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification. Deterministic versions of SSMs (e.g., LSTMs) proved extremely successful in modeling complex time-series data. Fully probabilistic SSMs, however, unfortunately often prove hard to train, even for smaller problems. To overcome this limitation, we propose a scalable initialization and training algorithm based on doubly stochastic variational inference and Gaussian processes. In the variational approximation we propose in contrast to related approaches to fully capture the latent state temporal correlations to allow for robust training.

Author(s): Andreas Doerr and Christian Daniel and Martin Schiegg and Duy Nguyen-Tuong and Stefan Schaal and Marc Toussaint and Sebastian Trimpe
Journal: ArXiv e-prints
Year: 2018
Month: January

Department(s): Autonomous Motion
Research Project(s): Learning Probabilistic Dynamics Models
Bibtex Type: Article (article)

Links: arXiv
Attachments: pdf


  title = {Probabilistic Recurrent State-Space Models},
  author = {Doerr, Andreas and Daniel, Christian and Schiegg, Martin and Nguyen-Tuong, Duy and Schaal, Stefan and Toussaint, Marc and Trimpe, Sebastian},
  journal = {ArXiv e-prints},
  month = jan,
  year = {2018},
  month_numeric = {1}