all research

Real Estate & Development · 8 min read

Proving an agent will behave: safety certification arrives for building controls

Reinforcement learning has beaten rule-based HVAC control for years. It has never been allowed near a real building, because nobody could guarantee what it would do. This paper certifies it after training.

67%

Comfort violation reduction, PPO

27.6%

Energy saving, SAC

Certified

Constraint satisfaction, post-training

Analysis of published research

Safe Deep Reinforcement Learning for Energy-Efficient HVAC Control in Multi-Zone Residential Buildings

Oussama Ziadi, Abdelilah Rochd, Samir Idrissi Kaitouni, Mohamed Oualid Mghazli, Adnane Saoud · arXiv · 18 August 2026

Reinforcement learning has been beating rule-based HVAC control in simulation for the best part of a decade. Almost none of it has reached a real building.

The reason is not performance. It is that a learned policy is a function nobody can read. Ask a facilities manager to hand temperature control of a residential block to a neural network and the first question is not how much energy it saves. It is what happens on the coldest night of the year when the model sees a state it was never trained on.

Nobody had a good answer. This paper offers one.

Certify after training, not during

Two agents were trained in EnergyPlus through the Sinergym interface, one using Proximal Policy Optimization and one using Soft Actor-Critic, both minimising energy while holding thermal comfort.

The contribution is what happens next. Post-training safety certification using Lipschitz-based forward invariance analysis, to guarantee constraint satisfaction. In plain terms: after the agent has finished learning, they prove mathematically that it cannot leave the safe region of operation.

The proof happens after the learning. You do not have to trust the training, only the certificate.
Reported results against rule-based control
percent improvement
Comfort violation reduction (PPO)67
Energy saving (SAC)27.6

Note that the two agents won different prizes. PPO cut comfort violations by 67%. SAC saved 27.6% of energy. That is a genuine trade-off rather than a single winner, and it is the trade-off a building owner has to make explicitly rather than discovering after handover.

Why this is the more important HVAC paper of the fortnight

There was a second HVAC paper published two days later, ADAPT, which I have written up separately. It posts good numbers on energy and comfort and solves a real deployment problem.

This one solves a procurement problem, and procurement is where building AI actually dies. A 27.6% saving does not get you past a risk committee. A guarantee might.

What to ask a vendor

Work with me

Run this model against your own project

I am Kanishk Kapoor, Technical Accounts Manager at AI Institute in Dublin. I build agentic AI systems with built-environment teams across Ireland and the UK. If any figure here looks wrong for your business, that is the useful conversation. Send me your assumptions and I will re-run it.

Continue reading