mlsanityData to 14 Oct 2026

Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks

arXiv 1605.07127 ↗First posted 23 May 2016stat.ML cs.LGcited by 49

Not on the map. Why?

Abstract (arXiv)

We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing α-divergences, allowing us to capture complicated statistical patterns in the transition dynamics, e.g. multi-modality and heteroskedasticity, which are usually missed by other common modeling approaches. We illustrate the performance of our method by solving a challenging benchmark where model-based approaches usually fail and by obtaining promising results in a real-world scenario for controlling a gas turbine.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 2; 2021: 13; 2022: 3; 2023: 14; 2024: 9; 2025: 3; 2026: 5.

49 papers.

Sort:

By area:

  1. 2020MOPO: Model-based Offline Policy Optimizationcited by 636
  2. 2023Reward Model Ensembles Help Mitigate Overoptimizationcited by 231
  3. 2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 185
  4. 2024Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknowncited by 74
  5. 2021Vector Quantized Models for Planningcited by 48
  6. 2020Overcoming Model Bias for Robust Offline Deep Reinforcement Learningcited by 43
  7. 2021Continuous-Time Model-Based Reinforcement Learningcited by 41
  8. 2021Few-shot Language Coordination by Modeling Theory of Mindcited by 32
  9. 2021Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Controlcited by 23
  10. 2021Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertaintycited by 19
  11. 2024Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaptioncited by 18
  12. 2021Propagating State Uncertainty Through Trajectory Forecastingcited by 17
37 more
  1. 2022Gluformer: Transformer-Based Personalized Glucose Forecasting with Uncertainty Quantificationcited by 17
  2. 2021Function-space Inference with Sparse Implicit Processescited by 13
  3. 2022User-Interactive Offline Reinforcement Learningcited by 11
  4. 2022Uncertainty Quantification for Deep Unrolling-Based Computational Imagingcited by 10
  5. 2023Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modelingcited by 10
  6. 2023Improving Offline RL by Blending Heuristicscited by 10
  7. 2023Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networkscited by 10
  8. 2023How to Learn and Generalize From Three Minutes of Data: Physics-Constrained and Uncertainty-Aware Neural Stochastic Differential Equationscited by 10
  9. 2021Certification of Iterative Predictions in Bayesian Neural Networkscited by 8
  10. 2024On Divergence Measures for Training GFlowNetscited by 6
  11. 2023Probabilistic Reach-Avoid for Bayesian Neural Networkscited by 5
  12. 2025Conformalized Generative Bayesian Imaging: An Uncertainty Quantification Framework for Computational Imagingcited by 5
  13. 2024FACTS: A Factored State-Space Framework For World Modellingcited by 4
  14. 2021Measuring Data Quality for Dataset Selection in Offline Reinforcement Learningcited by 3
  15. 2023Learning Control Policies for Variable Objectives from Offline Datacited by 3
  16. 2023Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learningcited by 3
  17. 2023CROP: Conservative Reward for Model-based Offline Policy Optimizationcited by 3
  18. 2025Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learningcited by 3
  19. 2021Learning to Reweight Imaginary Transitions for Model-Based Reinforcement Learningcited by 2
  20. 2021Federated Ensemble Model-based Reinforcement Learning in Edge Computingcited by 2
  21. 2023DiSProD: Differentiable Symbolic Propagation of Distributions for Planningcited by 2
  22. 2023A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Makingcited by 2
  23. 2023Sampling-Free Probabilistic Deep State-Space Modelscited by 2
  24. 2026Variational Neural Belief Parameterizations for Robust Dexterous Grasping under Multimodal Uncertaintycited by 2
  25. 2021Adaptive learning for financial markets mixing model-based and model-free RL for volatility targetingcited by 1
  26. 2023Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Componentscited by 1
  27. 2024Learning World Models With Hierarchical Temporal Abstractions: A Probabilistic Perspectivecited by 1
  28. 2024Mamba as Decision Maker: Exploring Multi-scale Sequence Modeling in Offline Reinforcement Learningcited by 1
  29. 2024Bounded Exploration with World Model Uncertainty in Soft Actor-Critic Reinforcement Learning Algorithmcited by 1
  30. 2025Combining Bayesian Inference and Reinforcement Learning for Agent Decision Making: A Reviewcited by 1
  31. 2026Uncertainty-Aware Reward Discounting for Mitigating Reward Hackingcited by 1
  32. 2023Quantifying Uncertainty in Deep Learning Classification with Noise in Discrete Inputs for Risk-Based Decision Makingcited by 0
  33. 2024Generative modeling of density regression through tree flowscited by 0
  34. 2024Mitigating Relative Over-Generalization in Multi-Agent Reinforcement Learningcited by 0
  35. 2026Stochastic Actor-Critic: Mitigating Overestimation via Temporal Aleatoric Uncertaintycited by 0
  36. 2026All Models are Wrong, Knowing Where is Useful: On Model Uncertainty in Reinforcement Learningcited by 0
  37. 2026Full-Covariance Smoothing of Bayesian Neural Networks for Online Adaptationcited by 0