mlsanityData to 14 Oct 2026

Probabilistic Recurrent State-Space Models

arXiv 1801.10395 ↗First posted 31 Jan 2018stat.MLcited by 64

Not on the map. Why?

Abstract (arXiv)

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, are often found hard to train, even for smaller problems. To overcome this limitation, we propose a novel model formulation and a scalable training algorithm based on doubly stochastic variational inference and Gaussian processes. In contrast to existing work, the proposed variational approximation allows one to fully capture the latent state temporal correlations. These correlations are the key to robust training. The effectiveness of the proposed PR-SSM is evaluated on a set of real-world benchmark datasets in comparison to state-of-the-art probabilistic model learning methods. Scalability and robustness are demonstrated on a high dimensional problem.

Key facts. Cited by 64 papers in the map (data through 14 Oct 2026). First posted on arXiv 31 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 14; 2022: 11; 2023: 15; 2024: 6; 2025: 6; 2026: 12.

64 papers.

Sort:

By area:

  1. 2024Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigationcited by 126
  2. 2023Video Prediction Models as Rewards for Reinforcement Learningcited by 78
  3. 2025Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)cited by 47
  4. 2023World Models via Policy-Guided Trajectory Diffusioncited by 34
  5. 2023Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Seriescited by 29
  6. 2022A Comprehensive Review of Digital Twin -- Part 1: Modeling and Twinning Enabling Technologiescited by 28
  7. 2023LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarioscited by 20
  8. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  9. 2021RNN with Particle Flow for Probabilistic Spatio-temporal Forecastingcited by 16
  10. 2022Flow-based Recurrent Belief State Learning for POMDPscited by 16
  11. 2021Variational multiple shooting for Bayesian ODEs with Gaussian processescited by 15
  12. 2022An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Contextcited by 15
38 more
  1. 2021High-Accuracy Model-Based Reinforcement Learning, a Surveycited by 13
  2. 2022On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learningcited by 13
  3. 2024R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Modelscited by 10
  4. 2024Amortized Control of Continuous State Space Feynman-Kac Model for Irregular Time Seriescited by 10
  5. 2021Structure-preserving Gaussian Process Dynamicscited by 9
  6. 2021GATSBI: Generative Agent-centric Spatio-temporal Object Interactioncited by 8
  7. 2022Recognition Models to Learn Dynamics from Partial Observations with Neural ODEscited by 8
  8. 2023On the Importance of Feature Decorrelation for Unsupervised Representation Learning in Reinforcement Learningcited by 8
  9. 2023Free-Form Variational Inference for Gaussian Process State-Space Modelscited by 7
  10. 2024OPa-Ma: Text Guided Mamba for 360-degree Image Out-paintingcited by 7
  11. 2022Deep Kernel Learning of Dynamical Models from High-Dimensional Noisy Datacited by 6
  12. 2022Output-Dependent Gaussian Process State-Space Modelcited by 6
  13. 2024Learning to Play Atari in a World of Tokenscited by 6
  14. 2021A Temporal Variational Model for Story Generationcited by 5
  15. 2022Recurrent Neural Networks and Universal Approximation of Bayesian Filterscited by 5
  16. 2023Towards Flexibility and Interpretability of Gaussian Process State-Space Modelcited by 5
  17. 2023Sequential Estimation of Gaussian Process-based Deep State-Space Modelscited by 5
  18. 2023Ensemble Kalman Filtering Meets Gaussian Process SSM for Non-Mean-Field and Online Inferencecited by 5
  19. 2021Learning What To Do by Simulating the Pastcited by 4
  20. 2022CtrlFormer: Learning Transferable State Representation for Visual Control via Transformercited by 4
  21. 2021Self-Supervised Inference in State-Space Modelscited by 3
  22. 2023Towards Efficient Modeling and Inference in Multi-Dimensional Gaussian Process State-Space Modelscited by 3
  23. 2023Exact Inference for Continuous-Time Gaussian Process Dynamicscited by 3
  24. 2021Active Learning in Gaussian Process State Space Modelcited by 2
  25. 2023Combining Slow and Fast: Complementary Filtering for Dynamics Learningcited by 2
  26. 2023Sampling-Free Probabilistic Deep State-Space Modelscited by 2
  27. 2025Efficient Transformed Gaussian Process State-Space Models for Non-Stationary High-Dimensional Dynamical Systemscited by 2
  28. 2026Latent Matters: Learning Deep State-Space Modelscited by 2
  29. 2021Likelihood-Free Inference in State-Space Models with Unknown Dynamicscited by 1
  30. 2022Continual Learning of Multi-modal Dynamics with External Memorycited by 1
  31. 2023Learning Mixture Structure on Multi-Source Time Series for Probabilistic Forecastingcited by 1
  32. 2023Learning IMM Filter Parameters from Measurements using Gradient Descentcited by 1
  33. 2025Double projection for reconstructing dynamical systems: between stochastic and deterministic regimescited by 1
  34. 2026The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modelingcited by 1
  35. 2021Long short-term relevance learningcited by 0
  36. 2021Dream to Explore: Adaptive Simulations for Autonomous Systemscited by 0
  37. 2021Switching Recurrent Kalman Networkscited by 0
  38. 2021Traversing Time with Multi-Resolution Gaussian Process State-Space Modelscited by 0

50 most cited of 64 All 64 (JSON)