mlsanityData to 7 Oct 2026

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

arXiv 2003.01283 ↗First posted 3 Mar 2020cs.LG cs.SY eess.SYcited by 0

On the map: Offline RL and imitation learning from data → Imitation learning methods

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.

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

16 of 59 references.

Closest ancestors · 1

Same direction, newest first

  1. 2018Safe end-to-end imitation learning for model predictive control27 Mar

Other references · 15

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2016Generative Adversarial Imitation Learningcited by 1,576
  3. 2015Weight Uncertainty in Neural Networkscited by 554
  4. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 203
  5. 2018Differentiable MPC for End-to-end Planning and Controlcited by 178
  6. 2018Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Controlcited by 104
  7. 2019PAC Confidence Sets for Deep Neural Networks via Calibrated Predictioncited by 59
  8. 2015Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Searchcited by 41
  9. 2016PLATO: Policy Learning using Adaptive Trajectory Optimizationcited by 23
  10. 2017DropoutDAgger: A Bayesian Approach to Safe Imitation Learningcited by 14
  11. 2017Representation and Reinforcement Learning for Personalized Glycemic Control in Septic Patientscited by 13
  12. 2017Safe Policy Search with Gaussian Process Modelscited by 9
3 more
  1. 2018Learning Confidence Sets using Support Vector Machinescited by 5
  2. 2019A Dual-Hormone Closed-Loop Delivery System for Type 1 Diabetes Using Deep Reinforcement Learningcited by 4
  3. 2017Data-Driven Robust Control for Type 1 Diabetes Under Meal and Exercise Uncertaintiescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Interventional Flow Matching: Prospective Dose-Response Forecasting with Velocity-Field Jacobian Regularization
  2. 2025Flexible Blood Glucose Control: Offline Reinforcement Learning from Human Feedback
  3. 2026From Prediction to Intervention: Personalized Meal-Level Glucose Regulation via an LLM Agent
  4. 2025Are Large Language Models Dynamic Treatment Planners? An In Silico Study from a Prior Knowledge Injection Angle
  5. 2026Behavioral Cloning Outperforms Entropy-Regularized RL: Critic-Driven Failure of Actor-Critic Methods on Adaptive Tumor Treatment
  6. 2026GUIDE: Reinforcement Learning for Behavioral Action Support in Type 1 Diabetes
  7. 2023End-to-end Offline Reinforcement Learning for Glycemia Control
  8. 2026Interpretable Language Model for Closed-Loop Type 1 Diabetes Control