# MPC-guided Imitation Learning of Neural Network Policies for the Artificial Pancreas

arXiv: https://arxiv.org/abs/2003.01283 · HTML: https://mlsanity.com/paper/2003.01283/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 16 of its 59 references that are in the map.
- First posted on arXiv 3 Mar 2020.

## Placed in

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

## Builds on (most cited first, 16 of 16)

- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Weight Uncertainty in Neural Networks](https://mlsanity.com/paper/1505.05424/) (2015)
- [Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learning](https://mlsanity.com/paper/1803.04765/) (2018)
- [Differentiable MPC for End-to-end Planning and Control](https://mlsanity.com/paper/1810.13400/) (2018)
- [Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control](https://mlsanity.com/paper/1811.01848/) (2018)
- [PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction](https://mlsanity.com/paper/2001.00106/) (2019)
- [Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search](https://mlsanity.com/paper/1509.06791/) (2015)
- [PLATO: Policy Learning using Adaptive Trajectory Optimization](https://mlsanity.com/paper/1603.00622/) (2016)
- [DropoutDAgger: A Bayesian Approach to Safe Imitation Learning](https://mlsanity.com/paper/1709.06166/) (2017)
- [Representation and Reinforcement Learning for Personalized Glycemic Control in Septic Patients](https://mlsanity.com/paper/1712.00654/) (2017)
- [Safe end-to-end imitation learning for model predictive control](https://mlsanity.com/paper/1803.10231/) (2018)
- [Safe Policy Search with Gaussian Process Models](https://mlsanity.com/paper/1712.05556/) (2017)
- [Learning Confidence Sets using Support Vector Machines](https://mlsanity.com/paper/1809.10818/) (2018)
- [A Dual-Hormone Closed-Loop Delivery System for Type 1 Diabetes Using Deep Reinforcement Learning](https://mlsanity.com/paper/1910.04059/) (2019)
- [Data-Driven Robust Control for Type 1 Diabetes Under Meal and Exercise Uncertainties](https://mlsanity.com/paper/1707.02246/) (2017)

## Abstract (arXiv)

Even though model predictive control (MPC) is currently the main algorithm for insulin control in the artificial pancreas (AP), it usually requires complex online optimizations, which are infeasible for resource-constrained medical devices. MPC also typically relies on state estimation, an error-prone process. In this paper, we introduce a novel approach to AP control that uses Imitation Learning to synthesize neural-network insulin policies from MPC-computed demonstrations. Such policies are computationally efficient and, by instrumenting MPC at training time with full state information, they can directly map measurements into optimal therapy decisions, thus bypassing state estimation. We apply Bayesian inference via Monte Carlo Dropout to learn policies, which allows us to quantify prediction uncertainty and thereby derive safer therapy decisions. We show that our control policies trained under a specific patient model readily generalize (in terms of model parameters and disturbance distributions) to patient cohorts, consistently outperforming traditional MPC with state estimation.