105 citations · 265 across the 13 of their papers we have counts for
4 papers · 1 filter
Towards Scalable Physically Consistent Neural Networks: an Application to Data-driven Multi-zone Thermal Building Models
Loris Di Natale, Bratislav Svetozarevic, Philipp Heer +1
With more and more data being collected, data-driven modeling methods have been gaining in popularity in recent years. While physically sound, classical gray-box models are often c…
Physically Consistent Neural ODEs for Learning Multi-Physics Systems
Muhammad Zakwan, Loris Di Natale, Bratislav Svetozarevic +3
Despite the immense success of neural networks in modeling system dynamics from data, they often remain physics-agnostic black boxes. In the particular case of physical systems, th…
Computationally Efficient Reinforcement Learning: Targeted Exploration leveraging Simple Rules
Loris Di Natale, Bratislav Svetozarevic, Philipp Heer +1
Model-free Reinforcement Learning (RL) generally suffers from poor sample complexity, mostly due to the need to exhaustively explore the state-action space to find well-performing…
Near-optimal Deep Reinforcement Learning Policies from Data for Zone Temperature Control
Loris Di Natale, Bratislav Svetozarevic, Philipp Heer +1
Replacing poorly performing existing controllers with smarter solutions will decrease the energy intensity of the building sector. Recently, controllers based on Deep Reinforcement…