mlsanityData to 7 Oct 2026

Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios

arXiv 2206.14697 ↗First posted 29 Jun 2022cs.LG cs.SY eess.SYcited by 8

Not on the map. Why?

Abstract (arXiv)

Recurrent State-space models (RSSMs) are highly expressive models for learning patterns in time series data and system identification. However, these models assume that the dynamics are fixed and unchanging, which is rarely the case in real-world scenarios. Many control applications often exhibit tasks with similar but not identical dynamics which can be modeled as a latent variable. We introduce the Hidden Parameter Recurrent State Space Models (HiP-RSSMs), a framework that parametrizes a family of related dynamical systems with a low-dimensional set of latent factors. We present a simple and effective way of learning and performing inference over this Gaussian graphical model that avoids approximations like variational inference. We show that HiP-RSSMs outperforms RSSMs and competing multi-task models on several challenging robotic benchmarks both on real-world systems and simulations.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 25 of its 50 references that are in the map. First posted on arXiv 29 Jun 2022.

Builds on

25 of 50 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  4. 2017Deep Setscited by 1,394
  5. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  6. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  7. 2020Planning to Explore via Self-Supervised World Modelscited by 365
  8. 2018Neural Processescited by 307
  9. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
  10. 2016Unsupervised Learning for Physical Interaction through Video Predictioncited by 256
  11. 2016Structured Inference Networks for Nonlinear State Space Modelscited by 182
  12. 2016Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Datacited by 154
13 more
  1. 2018Meta-Learning Probabilistic Inference For Predictioncited by 108
  2. 2017A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learningcited by 107
  3. 2018Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RLcited by 80
  4. 2013Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizationscited by 68
  5. 2019Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spacescited by 64
  6. 2016Backprop KF: Learning Discriminative Deterministic State Estimatorscited by 47
  7. 2018Meta Reinforcement Learning with Latent Variable Gaussian Processescited by 44
  8. 2020Learning to Play Table Tennis From Scratch using Muscular Robotscited by 31
  9. 2019Collapsed Amortized Variational Inference for Switching Nonlinear Dynamical Systemscited by 26
  10. 2019Switching Linear Dynamics for Variational Bayes Filteringcited by 17
  11. 2020Action-Conditional Recurrent Kalman Networks For Forward and Inverse Dynamics Learningcited by 13
  12. 2021Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Modelscited by 6
  13. 2016Transfer Learning Across Patient Variations with Hidden Parameter Markov Decision Processescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 0; 2026: 3.

8 papers.

  1. 2024Zero-Shot Reinforcement Learning via Function Encoderscited by 17
  2. 2024KalMamba: Towards Efficient Probabilistic State Space Models for RL under Uncertaintycited by 9
  3. 2023Multi Time Scale World Modelscited by 7
  4. 2024Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observabilitycited by 5
  5. 2026Offline Reinforcement Learning for Rotation Profile Control in Tokamakscited by 2
  6. 2024Adaptive World Models: Learning Behaviors by Latent Imagination Under Non-Stationaritycited by 0
  7. 2026Beyond Multimodal Alignment: Certifying Physical Language through Response Substitution and Ordered Executioncited by 0
  8. 2026Shaping Persistent Representations from Independent Interactionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024HiPPO-Prophecy: State-Space Models can Provably Learn Dynamical Systems in Context
  2. 2024Deep Learning-based Approaches for State Space Models: A Selective Review
  3. 2026On the Relation of State Space Models and Hidden Markov Models
  4. 2026Correct then Forecast: Observer State-Space Models for Time Series Forecasting
  5. 2025Maximum Likelihood Learning of Latent Dynamics Without Reconstruction
  6. 2026Physics-Guided Recurrent State-Space Neural Networks for Multi-Step Prediction
  7. 2024Towards a theory of learning dynamics in deep state space models
  8. 2026MaRK: Markov-adapted Recurrent Kernels for Dynamic Operator Conditioning in State Space Models