mlsanityData to 14 Oct 2026

Continual Reinforcement Learning for HVAC Systems Control: Integrating Hypernetworks and Transfer Learning

arXiv 2503.19212 ↗First posted 24 Mar 2025cs.LG cs.AI cs.SYcited by 1

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

Abstract (arXiv)

Buildings with Heating, Ventilation, and Air Conditioning (HVAC) systems play a crucial role in ensuring indoor comfort and efficiency. While traditionally governed by physics-based models, the emergence of big data has enabled data-driven methods like Deep Reinforcement Learning (DRL). However, Reinforcement Learning (RL)-based techniques often suffer from sample inefficiency and limited generalization, especially across varying HVAC systems. We introduce a model-based reinforcement learning framework that uses a Hypernetwork to continuously learn environment dynamics across tasks with different action spaces. This enables efficient synthetic rollout generation and improved sample usage. Our approach demonstrates strong backward transfer in a continual learning setting after training on a second task, minimal fine-tuning on the first task allows rapid convergence within just 5 episodes and thus outperforming Model Free Reinforcement Learning (MFRL) and effectively mitigating catastrophic forgetting. These findings have significant implications for reducing energy consumption and operational costs in building management, thus supporting global sustainability goals. Keywords: Deep Reinforcement Learning, HVAC Systems Control, Hypernetworks, Transfer and Continual Learning, Catastrophic Forgetting

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 11 of its 20 references that are in the map. First posted on arXiv 24 Mar 2025.

Builds on

11 of 20 references.

References · 11

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  3. 2019A Comprehensive Survey on Transfer Learningcited by 1,160
  4. 2018Experience Replay for Continual Learningcited by 1,095
  5. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 872
  6. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  7. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  8. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 364
  9. 2019Continual learning with hypernetworkscited by 273
  10. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  11. 2020One for Many: Transfer Learning for Building HVAC Controlcited by 16

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Heating in human-HVAC interaction for smart homes: An interdisciplinary overviewcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Building2Building: A Large Scale Benchmark for Generalizable Real-World Reinforcement Learning
  2. 2026Hierarchical Control Framework Integrating LLMs with RL for Decarbonized HVAC Operation
  3. 2024An experimental evaluation of Deep Reinforcement Learning algorithms for HVAC control
  4. 2026Generalizing HVAC Control With Domain Randomized Reinforcement Learning
  5. 2024Employing Federated Learning for Training Autonomous HVAC Systems
  6. 2025Reinforcement Learning (RL) Meets Urban Climate Modeling: Investigating the Efficacy and Impacts of RL-Based HVAC Control
  7. 2026Counter-Dyna: Data-Efficient RL-Based HVAC Control using Counterfactual Building Models
  8. 2026Safe Deep Reinforcement Learning for Energy-Efficient HVAC Control in Multi-Zone Residential Buildings