# A Sensitivity-based Data Augmentation Framework for Model Predictive Control Policy Approximation

arXiv: https://arxiv.org/abs/2009.07398 · HTML: https://mlsanity.com/paper/2009.07398/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2020.

## Built on by (most cited first, 6 of 6)

- [Parameter-Adaptive Approximate MPC: Tuning Neural-Network Controllers without Retraining](https://mlsanity.com/paper/2404.05835/) (2024)
- [An Improved Data Augmentation Scheme for Model Predictive Control Policy Approximation](https://mlsanity.com/paper/2303.05607/) (2023)
- [Imitation Learning of MPC with Neural Networks: Error Guarantees and Sparsification](https://mlsanity.com/paper/2501.03671/) (2025)
- [On Building Myopic MPC Policies using Supervised Learning](https://mlsanity.com/paper/2401.12546/) (2024)
- [Approximate Model Predictive Control for Microgrid Energy Management via Imitation Learning](https://mlsanity.com/paper/2510.20040/) (2025)
- [ReLU Networks for Model Predictive Control: Network Complexity and Performance Guarantees](https://mlsanity.com/paper/2601.16764/) (2026)

## Abstract (arXiv)

Approximating model predictive control (MPC) policy using expert-based supervised learning techniques requires labeled training data sets sampled from the MPC policy. This is typically obtained by sampling the feasible state-space and evaluating the control law by solving the numerical optimization problem offline for each sample. Although the resulting approximate policy can be cheaply evaluated online, generating large training samples to learn the MPC policy can be time consuming and prohibitively expensive. This is one of the fundamental bottlenecks that limit the design and implementation of MPC policy approximation. This technical note aims to address this challenge, and proposes a novel sensitivity-based data augmentation scheme for direct policy approximation. The proposed approach is based on exploiting the parametric sensitivities to cheaply generate additional training samples in the neighborhood of the existing samples.