HVAC-GRACE: Transferable Building Control via Heterogeneous Graph Neural Network Policies

Anaïs Berkes, Donna Vakalis, David Rolnick, Yoshua Bengio

Keywords: Building Control, Graphs, Reinforcement Learning, Transfer Learning

TL;DR: HVAC-GRACE introduces a graph-based reinforcement learning framework that models buildings as heterogeneous graphs to enable transferable HVAC control across different building topologies.

Abstract:

Buildings consume 40% of global energy, with HVAC systems responsible for up to half of that demand. As energy use grows, optimizing HVAC efficiency is critical to meeting climate goals. While reinforcement learning (RL) offers a promising alternative to rule-based control, real-world adoption is limited by poor sample efficiency and generalisation.
We introduce HVAC-GRACE, a graph-based RL framework that models buildings as heterogeneous graphs and integrates spatial message passing directly into temporal GRU gates. This enables each zone to learn control actions informed by both its own history and its structural context.
Our architecture supports zero-shot transfer by learning topology-agnostic functions—but initial experiments reveal that this benefit depends on sufficient conditioned zone connectivity to maintain gradient flow. These findings highlight both the promise and the architectural requirements of scalable, transferable RL for building control

Submission Number: 19