mlsanityData to 14 Oct 2026

Data-Driven Policy Mapping for Safe RL-based Energy Management Systems

arXiv 2506.16352 ↗First posted 19 Jun 2025cs.LGcited by 1

On the map: Deep reinforcement learning methods → RL for energy, networks and operations

Abstract (arXiv)

Increasing global energy demand and renewable integration complexity have placed buildings at the center of sustainable energy management. We present a three-step reinforcement learning(RL)-based Building Energy Management System (BEMS) that combines clustering, forecasting, and constrained policy learning to address scalability, adaptability, and safety challenges. First, we cluster non-shiftable load profiles to identify common consumption patterns, enabling policy generalization and transfer without retraining for each new building. Next, we integrate an LSTM based forecasting module to anticipate future states, improving the RL agents' responsiveness to dynamic conditions. Lastly, domain-informed action masking ensures safe exploration and operation, preventing harmful decisions. Evaluated on real-world data, our approach reduces operating costs by up to 15% for certain building types, maintains stable environmental performance, and quickly classifies and optimizes new buildings with limited data. It also adapts to stochastic tariff changes without retraining. Overall, this framework delivers scalable, robust, and cost-effective building energy management.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 13 of its 118 references that are in the map. First posted on arXiv 19 Jun 2025.

Builds on

13 of 118 references.

References · 13

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2015Trust Region Policy Optimizationcited by 2,580
  5. 2017Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithmcited by 734
  6. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  7. 2020A Closer Look at Invalid Action Masking in Policy Gradient Algorithmscited by 171
  8. 2016Playing FPS Games with Deep Reinforcement Learningcited by 95
  9. 2020Sample Efficient Reinforcement Learning with REINFORCEcited by 86
  10. 2021Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challengescited by 50
  11. 2020A Review of Deep Reinforcement Learning for Smart Building Energy Managementcited by 38
  12. 2019Deep Reinforcement Learning for Smart Home Energy Managementcited by 30
1 more
  1. 2021Data-driven Model Predictive and Reinforcement Learning Based Control for Building Energy Management: a Surveycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Meta-RL with Shared Representations Enables Fast Adaptation in Energy Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Explainable Data-driven Deep Reinforcement Learning Methods for Optimal Energy Management in Buildings
  2. 2025BuildingGym: An open-source toolbox for AI-based building energy management using reinforcement learning
  3. 2024Optimal Management of Grid-Interactive Efficient Buildings via Safe Reinforcement Learning
  4. 2024Distill2Explain: Differentiable decision trees for explainable reinforcement learning in energy application controllers
  5. 2026Hierarchical Control Framework Integrating LLMs with RL for Decarbonized HVAC Operation
  6. 2026Supervised Reinforcement Learning for the Coordination of Distributed Energy Resources
  7. 2025A Reinforcement Learning Approach for Optimal Control in Microgrids
  8. 2024Reinforcement Learning for Efficient Design and Control Co-optimisation of Energy Systems