The authors designed a challenge to address the lack of policy transfer in building control.
Competition challenges AI models to optimize HVAC control across unfamiliar buildings
Goldfeder et al. propose a benchmark where control policies trained on simulated buildings are scored on unseen buildings and climate stations to test transfer.
Big Tech
Judah Goldfeder · Ayush Rai · Philippe M. Wyder · Na Li · Victoria Dean · Donna Vakalis · +8 more
Columbia University · Harvard University · Distyl AI · Princeton University · Mila
Research Digest··3 min read
The authors introduce a competition built on the Smart Buildings Control Suite, in which participants train HVAC control policies on procedurally generated simulated buildings and are evaluated on held-out buildings and climates.
Why this paper
From Google and 8 others
In one line
A procedural HVAC benchmark measures whether one controller can transfer across unseen building designs and climates with minimal per-building configuration.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§