# Reinforced Model Predictive Control via Trust-Region Quasi-Newton Policy Optimization

arXiv: https://arxiv.org/abs/2405.17983 · HTML: https://mlsanity.com/paper/2405.17983/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods.
- Builds on 5 of its 27 references that are in the map.
- First posted on arXiv 28 May 2024.

## Placed in

- Deep reinforcement learning methods / [RL for autonomous driving and traffic](https://mlsanity.com/deeprl/rl-for-autonomous-driving-and-traffic/)

## Builds on (most cited first, 5 of 5)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Data-driven Economic NMPC using Reinforcement Learning](https://mlsanity.com/paper/1904.04152/) (2019)
- [Quasi-Newton Trust Region Policy Optimization](https://mlsanity.com/paper/1912.11912/) (2019)
- [Quasi-Newton Iteration in Deterministic Policy Gradient](https://mlsanity.com/paper/2203.13854/) (2022)

## Built on by (most cited first, 4 of 4)

- [Sample-Efficient Reinforcement Learning of Koopman eNMPC](https://mlsanity.com/paper/2503.18787/) (2025)
- [Computationally efficient Gauss-Newton reinforcement learning for model predictive control](https://mlsanity.com/paper/2508.02441/) (2025)
- [Optimizing Operation Recipes with Reinforcement Learning for Safe and Interpretable Control of Chemical Processes](https://mlsanity.com/paper/2511.16297/) (2025)
- [Direct transfer of optimized controllers to similar systems using dimensionless MPC](https://mlsanity.com/paper/2512.08667/) (2025)

## Abstract (arXiv)

Model predictive control can optimally deal with nonlinear systems under consideration of constraints. The control performance depends on the model accuracy and the prediction horizon. Recent advances propose to use reinforcement learning applied to a parameterized model predictive controller to recover the optimal control performance even if an imperfect model or short prediction horizons are used. However, common reinforcement learning algorithms rely on first order updates, which only have a linear convergence rate and hence need an excessive amount of dynamic data. Higher order updates are typically intractable if the policy is approximated with neural networks due to the large number of parameters. In this work, we use a parameterized model predictive controller as policy, and leverage the small amount of necessary parameters to propose a trust-region constrained Quasi-Newton training algorithm for policy optimization with a superlinear convergence rate. We show that the required second order derivative information can be calculated by the solution of a linear system of equations. A simulation study illustrates that the proposed training algorithm outperforms other algorithms in terms of data efficiency and accuracy.