# Efficient Deep Learning of Robust Policies from MPC using Imitation and Tube-Guided Data Augmentation

arXiv: https://arxiv.org/abs/2306.00286 · HTML: https://mlsanity.com/paper/2306.00286/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- First posted on arXiv 1 Jun 2023.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

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

- [YANNs: Y-wise Affine Neural Networks for Exact and Efficient Representations of Piecewise Linear Functions](https://mlsanity.com/paper/2505.07054/) (2025)
- [TamedPUMA: safe and stable imitation learning with geometric fabrics](https://mlsanity.com/paper/2503.17432/) (2025)
- [Bridging the Sim-to-real Gap: A Control Framework for Imitation Learning of Model Predictive Control](https://mlsanity.com/paper/2503.19228/) (2025)
- [Feedback-MPPI: Fast Sampling-Based MPC via Rollout Differentiation -- Adios low-level controllers](https://mlsanity.com/paper/2506.14855/) (2025)
- [Aerobatic maneuvers in insect-scale flapping-wing aerial robots via deep-learned robust tube model predictive control](https://mlsanity.com/paper/2508.03043/) (2025)
- [Distributionally Robust and Safe Imitation Learning](https://mlsanity.com/paper/2607.13436/) (2026)

## Abstract (arXiv)

Imitation Learning (IL) can generate computationally efficient policies from demonstrations provided by Model Predictive Control (MPC). However, IL methods often require extensive data-collection and training efforts, limiting changes to the policy if the task changes, and they produce policies with limited robustness to new disturbances. In this work, we propose an IL strategy to efficiently compress a computationally expensive MPC into a deep neural network policy that is robust to previously unseen disturbances. By using a robust variant of the MPC, called Robust Tube MPC, and leveraging properties from the controller, we introduce computationally efficient data augmentation methods that enable a significant reduction of the number of MPC demonstrations and training efforts required to generate a robust policy. Our approach opens the possibility of zero-shot transfer of a policy trained from a single MPC demonstration collected in a nominal domain, such as a simulation or a robot in a lab/controlled environment, to a new domain with previously unseen bounded model errors/perturbations. Numerical evaluations performed using linear and nonlinear MPC for agile flight on a multirotor show that our method outperforms strategies commonly employed in IL (such as Dataset-Aggregation (DAgger) and Domain Randomization (DR)) in terms of demonstration-efficiency, training time, and robustness to perturbations unseen during training. Experimental evaluations validate the efficiency and real-world robustness.