Reinforcement Learning for Building Control and its Real-World Implementation

Andrey Bernstein, Xiangyu Zhang, Rohit Chintala, Yue Chen, Xin Jin, Peter Graf, Gregor Henze, Emiliano Dall'Anese, Sourav Dey, Thibault Marzullo, Ana Ospina

Research output: NRELPoster


This presentation compares the performance of reinforcement learning controller with model predictive control for a real-world New York high rise building with 40 floors.
Original languageAmerican English
PublisherNational Renewable Energy Laboratory (NREL)
StatePublished - 2023

Publication series

NamePresented at the 2023 Department of Energy (DOE) Building Technologies Office (BTO) Peer Review, 24-28 April 2023, Arlington, Virginia

NREL Publication Number

  • NREL/PO-5500-85670


  • grid efficient buildings
  • model predictive control
  • reinforcement learning


Dive into the research topics of 'Reinforcement Learning for Building Control and its Real-World Implementation'. Together they form a unique fingerprint.

Cite this