# Bayesian Learning Approach to Model Predictive Control

arXiv: https://arxiv.org/abs/2203.02720 · HTML: https://mlsanity.com/paper/2203.02720/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 5 Mar 2022.

## Builds on (most cited first, 9 of 9)

- [New insights and perspectives on the natural gradient method](https://mlsanity.com/paper/1412.1193/) (2014)
- [The Bayesian Learning Rule](https://mlsanity.com/paper/2107.04562/) (2021)
- [Information Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving](https://mlsanity.com/paper/1707.02342/) (2017)
- [The Power of Predictions in Online Control](https://mlsanity.com/paper/2006.07569/) (2020)
- [An Online Learning Approach to Model Predictive Control](https://mlsanity.com/paper/1902.08967/) (2019)
- [Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems](https://mlsanity.com/paper/2106.10497/) (2021)
- [Lessons from AlphaZero for Optimal, Model Predictive, and Adaptive Control](https://mlsanity.com/paper/2108.10315/) (2021)
- [Robust Model Predictive Path Integral Control: Analysis and Performance Guarantees](https://mlsanity.com/paper/2102.09027/) (2021)
- [Dynamic Mirror Descent based Model Predictive Control for Accelerating Robot Learning](https://mlsanity.com/paper/2112.02999/) (2021)

## Built on by (most cited first, 1 of 1)

- [Optimizing Social Utility in Sequential Experiments](https://mlsanity.com/paper/2605.06520/) (2026)

## Abstract (arXiv)

This study presents a Bayesian learning perspective towards model predictive control algorithms. High-level frameworks have been developed separately in the earlier studies on Bayesian learning and sampling-based model predictive control. On one hand, the Bayesian learning rule provides a general framework capable of generating various machine learning algorithms as special instances. On the other hand, the dynamic mirror descent model predictive control framework is capable of diversifying sample-rollout-based control algorithms. However, connections between the two frameworks have still not been fully appreciated in the context of stochastic optimal control. This study combines the Bayesian learning rule point of view into the model predictive control setting by taking inspirations from the view of understanding model predictive controller as an online learner. The selection of posterior class and natural gradient approximation for the variational formulation governs diversification of model predictive control algorithms in the Bayesian learning approach to model predictive control. This alternative viewpoint complements the dynamic mirror descent framework through streamlining the explanation of design choices.