Presentation
Go Beyond Black-box Policies: Rethinking the Design of Learning Agent for Interpretable and Verifiable HVAC Control
DescriptionRecent research has shown the potential of Model-based Reinforcement Learning (MBRL) to enhance energy efficiency of Heating, Ventilation, and Air Conditioning (HVAC) systems. However, existing methods rely on black-box thermal dynamics models and stochastic optimizers, lacking reliability guarantees and posing risks to occupant health. We address this by redesigning HVAC controllers using decision trees extracted from thermal models and historical data, providing deterministic, verifiable, and interpretable policies. Extensive experiments show that our method saves 68.4% more energy and increases human comfort gain by 14.8% compared to the state-of-the-art method, plus a 1127x reduction in computation overhead. Code: https://github.com/30363/Veri-HVAC.
Event Type
Research Manuscript
TimeTuesday, June 2511:45am - 12:00pm PDT
Location3001, 3rd Floor
AI
AI/ML Algorithms