mlsanityData to 14 Oct 2026

Fine-tuning for Data-enabled Predictive Control of Noisy Systems by Reinforcement Learning

arXiv 2505.24572 ↗First posted 30 May 2025math.OCcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Data-enabled predictive control (DeePC) leverages system measurements in characterizing system dynamics for optimal control. The performance of DeePC relies on optimizing its hyperparameters, especially in noisy systems where the optimal hyperparameters adapt over time. Existing hyperparameter tuning approaches for DeePC are more than often computationally inefficient or overly conservative. This paper proposes an adaptive DeePC where we guide its hyperparameters adaption through reinforcement learning. We start with establishing the relationship between the system I/O behavior and DeePC hyperparameters. Then we formulate the hyperparameter tuning as a sequential decision-making problem, and we address the decision-making through reinforcement learning. We implement offline training to gain a reinforcement learning model, and we integrate the trained model with DeePC to adjust its hyperparameters adaptively in real time. We conduct numerical simulations with diverse noisy conditions, and the results demonstrate the identification of near-optimal hyperparameters and the robustness of the proposed approach against noises in the control.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 25 of its 82 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

25 of 82 references.

References · 25

  1. 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 145
  2. 2019Data informativity: a new perspective on data-driven analysis and controlcited by 19
  3. 2020Distributionally Robust Chance Constrained Data-enabled Predictive Controlcited by 16
  4. 2022Robust and Kernelized Data-Enabled Predictive Control for Nonlinear Systemscited by 9
  5. 2022Extended vehicle energy dataset (eVED): an enhanced large-scale dataset for deep learning on vehicle trip energy consumptioncited by 5
  6. 2021Robust Data-Enabled Predictive Control: Tractable Formulations and Performance Guaranteescited by 4
  7. 2023Harnessing Uncertainty for a Separation Principle in Direct Data-Driven Predictive Controlcited by 4
  8. 2024A Bionic Data-driven Approach for Long-distance Underwater Navigation with Anomaly Resistancecited by 4
  9. 2025AI-Driven Diabetic Retinopathy Diagnosis Enhancement through Image Processing and Salp Swarm Algorithm-Optimized Ensemble Networkcited by 3
  10. 2019Decentralized Data-Enabled Predictive Control for Power System Oscillation Dampingcited by 2
  11. 2021An Energy Consumption Model for Electrical Vehicle Networks via Extended Federated-learningcited by 2
  12. 2022Active learning for anti-disturbance dual control of unknown nonlinear systemscited by 2
13 more
  1. 2023Physics-Augmented Data-EnablEd Predictive Control for Eco-driving of Mixed Traffic Considering Diverse Human Behaviorscited by 2
  2. 2023Adaptive robust tracking control with active learning for linear systems with ellipsoidal bounded uncertaintiescited by 2
  3. 2024Ensemble Control for Stochastic Systems with Asymmetric Laplace Noisescited by 2
  4. 2024Long-distance Geomagnetic Navigation in GNSS-denied Environments with Deep Reinforcement Learningcited by 2
  5. 2024DeePC-Hunt: Data-enabled Predictive Control Hyperparameter Tuning via Differentiable Optimizationcited by 2
  6. 2025Exploring the Generalizability of Geomagnetic Navigation: A Deep Reinforcement Learning approach with Policy Distillationcited by 2
  7. 2025Temperature-Driven Robust Disease Detection in Brain and Gastrointestinal Disorders via Context-Aware Adaptive Knowledge Distillationcited by 2
  8. 2020An Extended Kalman Filter for Data-enabled Predictive Controlcited by 1
  9. 2021Data-driven predictive control with improved performance using segmented trajectoriescited by 1
  10. 2024On the equivalence of direct and indirect data-driven predictive control approachescited by 1
  11. 2024Hardware-in-the-loop Simulation Testbed for Geomagnetic Navigationcited by 1
  12. 2025Hybrid Data-enabled Predictive Control: Incorporating model knowledge into the DeePCcited by 1
  13. 2025Adaptive Fault-tolerant Control of Underwater Vehicles with Thruster Failurescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025HyperController: A Hyperparameter Controller for Fast and Stable Training of Reinforcement Learning Neural Networks
  2. 2025HypeRL: Hypernetwork-Based Reinforcement Learning for Control of Parametrized Dynamical Systems
  3. 2024The Cross-environment Hyperparameter Setting Benchmark for Reinforcement Learning
  4. 2025From Shadow to Light: Toward Safe and Efficient Policy Learning Across MPC, DeePC, RL, and LLM Agents
  5. 2025Leveraging Reinforcement Learning and Koopman Theory for Enhanced Model Predictive Control Performance
  6. 2024Efficient Exploration in Deep Reinforcement Learning: A Novel Bayesian Actor-Critic Algorithm
  7. 2025On Architectures for Combining Reinforcement Learning and Model Predictive Control with Runtime Improvements
  8. 2024A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning