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

arXiv: https://arxiv.org/abs/1605.07127 · HTML: https://mlsanity.com/paper/1605.07127/

## Key facts

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

## Built on by (most cited first, 30 of 49)

- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [Reward Model Ensembles Help Mitigate Overoptimization](https://mlsanity.com/paper/2310.02743/) (2023)
- [RvS: What is Essential for Offline RL via Supervised Learning?](https://mlsanity.com/paper/2112.10751/) (2021)
- [Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown](https://mlsanity.com/paper/2410.00847/) (2024)
- [Vector Quantized Models for Planning](https://mlsanity.com/paper/2106.04615/) (2021)
- [Overcoming Model Bias for Robust Offline Deep Reinforcement Learning](https://mlsanity.com/paper/2008.05533/) (2020)
- [Continuous-Time Model-Based Reinforcement Learning](https://mlsanity.com/paper/2102.04764/) (2021)
- [Few-shot Language Coordination by Modeling Theory of Mind](https://mlsanity.com/paper/2107.05697/) (2021)
- [Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control](https://mlsanity.com/paper/2108.00128/) (2021)
- [Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty](https://mlsanity.com/paper/2104.12446/) (2021)
- [Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption](https://mlsanity.com/paper/2405.19014/) (2024)
- [Propagating State Uncertainty Through Trajectory Forecasting](https://mlsanity.com/paper/2110.03267/) (2021)
- [Gluformer: Transformer-Based Personalized Glucose Forecasting with Uncertainty Quantification](https://mlsanity.com/paper/2209.04526/) (2022)
- [Function-space Inference with Sparse Implicit Processes](https://mlsanity.com/paper/2110.07618/) (2021)
- [User-Interactive Offline Reinforcement Learning](https://mlsanity.com/paper/2205.10629/) (2022)
- [Uncertainty Quantification for Deep Unrolling-Based Computational Imaging](https://mlsanity.com/paper/2207.00698/) (2022)
- [Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling](https://mlsanity.com/paper/2302.01312/) (2023)
- [Improving Offline RL by Blending Heuristics](https://mlsanity.com/paper/2306.00321/) (2023)
- [Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks](https://mlsanity.com/paper/2306.05674/) (2023)
- [How to Learn and Generalize From Three Minutes of Data: Physics-Constrained and Uncertainty-Aware Neural Stochastic Differential Equations](https://mlsanity.com/paper/2306.06335/) (2023)
- [Certification of Iterative Predictions in Bayesian Neural Networks](https://mlsanity.com/paper/2105.10134/) (2021)
- [On Divergence Measures for Training GFlowNets](https://mlsanity.com/paper/2410.09355/) (2024)
- [Probabilistic Reach-Avoid for Bayesian Neural Networks](https://mlsanity.com/paper/2310.01951/) (2023)
- [Conformalized Generative Bayesian Imaging: An Uncertainty Quantification Framework for Computational Imaging](https://mlsanity.com/paper/2504.07696/) (2025)
- [FACTS: A Factored State-Space Framework For World Modelling](https://mlsanity.com/paper/2410.20922/) (2024)
- [Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning](https://mlsanity.com/paper/2111.13461/) (2021)
- [Learning Control Policies for Variable Objectives from Offline Data](https://mlsanity.com/paper/2308.06127/) (2023)
- [Mind the Uncertainty: Risk-Aware and Actively Exploring Model-Based Reinforcement Learning](https://mlsanity.com/paper/2309.05582/) (2023)
- [CROP: Conservative Reward for Model-based Offline Policy Optimization](https://mlsanity.com/paper/2310.17245/) (2023)
- [Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learning](https://mlsanity.com/paper/2503.20139/) (2025)

## 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.