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

arXiv: https://arxiv.org/abs/2512.18317 · HTML: https://mlsanity.com/paper/2512.18317/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 20 Dec 2025.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Builds on (most cited first, 20 of 20)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Constrained Policy Optimization](https://mlsanity.com/paper/1705.10528/) (2017)
- [Challenges of Real-World Reinforcement Learning](https://mlsanity.com/paper/1904.12901/) (2019)
- [Explaining Reinforcement Learning with Shapley Values](https://mlsanity.com/paper/2306.05810/) (2023)
- [A Survey on Explainable Deep Reinforcement Learning](https://mlsanity.com/paper/2502.06869/) (2025)
- [Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation](https://mlsanity.com/paper/2405.20860/) (2024)
- [Control-Informed Reinforcement Learning for Chemical Processes](https://mlsanity.com/paper/2408.13566/) (2024)
- [Distill2Explain: Differentiable decision trees for explainable reinforcement learning in energy application controllers](https://mlsanity.com/paper/2403.11907/) (2024)
- [Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time](https://mlsanity.com/paper/2405.14183/) (2024)
- [Data Center Cooling System Optimization Using Offline Reinforcement Learning](https://mlsanity.com/paper/2501.15085/) (2025)
- [Reinforcement Learning for Efficient Design and Control Co-optimisation of Energy Systems](https://mlsanity.com/paper/2406.19825/) (2024)
- [Multi-Objective Reinforcement Learning for Energy-Efficient Industrial Control](https://mlsanity.com/paper/2505.07607/) (2025)
- [Towards Optimal Energy Management Strategy for Hybrid Electric Vehicle with Reinforcement Learning](https://mlsanity.com/paper/2305.12365/) (2023)
- [Demystifying Reinforcement Learning in Production Scheduling via Explainable AI](https://mlsanity.com/paper/2408.09841/) (2024)
- [Leveraging Reinforcement Learning and Koopman Theory for Enhanced Model Predictive Control Performance](https://mlsanity.com/paper/2505.08122/) (2025)

## 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.