mlsanityData to 7 Oct 2026

Trustworthy and Explainable Deep Reinforcement Learning for Safe and Energy-Efficient Process Control: A Use Case in Industrial Compressed Air Systems

arXiv 2512.18317 ↗First posted 20 Dec 2025cs.LG cs.AI cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents a trustworthy reinforcement learning approach for the control of industrial compressed air systems. We develop a framework that enables safe and energy-efficient operation under realistic boundary conditions and introduce a multi-level explainability pipeline combining input perturbation tests, gradient-based sensitivity analysis, and SHAP (SHapley Additive exPlanations) feature attribution. An empirical evaluation across multiple compressor configurations shows that the learned policy is physically plausible, anticipates future demand, and consistently respects system boundaries. Compared to the installed industrial controller, the proposed approach reduces unnecessary overpressure and achieves energy savings of approximately 4,% without relying on explicit physics models. The results further indicate that system pressure and forecast information dominate policy decisions, while compressor-level inputs play a secondary role. Overall, the combination of efficiency gains, predictive behavior, and transparent validation supports the trustworthy deployment of reinforcement learning in industrial energy systems.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 38 references that are in the map. First posted on arXiv 20 Dec 2025.

Builds on

20 of 38 references.

References · 20

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  5. 2017Deep reinforcement learning from human preferencescited by 3,846
  6. 2015Continuous control with deep reinforcement learningcited by 3,279
  7. 2017Constrained Policy Optimizationcited by 928
  8. 2019Challenges of Real-World Reinforcement Learningcited by 282
  9. 2023Explaining Reinforcement Learning with Shapley Valuescited by 26
  10. 2025A Survey on Explainable Deep Reinforcement Learningcited by 12
  11. 2024Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulationcited by 8
  12. 2024Control-Informed Reinforcement Learning for Chemical Processescited by 6
8 more
  1. 2024Distill2Explain: Differentiable decision trees for explainable reinforcement learning in energy application controllerscited by 5
  2. 2024Deterministic Policies for Constrained Reinforcement Learning in Polynomial Timecited by 5
  3. 2025Data Center Cooling System Optimization Using Offline Reinforcement Learningcited by 4
  4. 2024Reinforcement Learning for Efficient Design and Control Co-optimisation of Energy Systemscited by 2
  5. 2025Multi-Objective Reinforcement Learning for Energy-Efficient Industrial Controlcited by 2
  6. 2023Towards Optimal Energy Management Strategy for Hybrid Electric Vehicle with Reinforcement Learningcited by 1
  7. 2024Demystifying Reinforcement Learning in Production Scheduling via Explainable AIcited by 1
  8. 2025Leveraging Reinforcement Learning and Koopman Theory for Enhanced Model Predictive Control Performancecited by 1

Built on by

Not cited yet.