English

Higher-Order Action Regularization in Deep Reinforcement Learning: From Continuous Control to Building Energy Management

Artificial Intelligence 2026-01-06 v1 Machine Learning

Abstract

Deep reinforcement learning agents often exhibit erratic, high-frequency control behaviors that hinder real-world deployment due to excessive energy consumption and mechanical wear. We systematically investigate action smoothness regularization through higher-order derivative penalties, progressing from theoretical understanding in continuous control benchmarks to practical validation in building energy management. Our comprehensive evaluation across four continuous control environments demonstrates that third-order derivative penalties (jerk minimization) consistently achieve superior smoothness while maintaining competitive performance. We extend these findings to HVAC control systems where smooth policies reduce equipment switching by 60%, translating to significant operational benefits. Our work establishes higher-order action regularization as an effective bridge between RL optimization and operational constraints in energy-critical applications.

Keywords

Cite

@article{arxiv.2601.02061,
  title  = {Higher-Order Action Regularization in Deep Reinforcement Learning: From Continuous Control to Building Energy Management},
  author = {Faizan Ahmed and Aniket Dixit and James Brusey},
  journal= {arXiv preprint arXiv:2601.02061},
  year   = {2026}
}

Comments

6 pages, accepted at NeurIPS workshop 2025

R2 v1 2026-07-01T08:50:47.381Z