An asymmetric, node-by-node grown soft decision tree distilled from a DQN heat pump controller uses fewer nodes than a full tree while matching teacher performance more closely.
Methodology for interpretable reinforcement learning model for hvac energy control
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
eess.SY 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Interpretable reinforcement learning for heat pump control through asymmetric differentiable decision trees
An asymmetric, node-by-node grown soft decision tree distilled from a DQN heat pump controller uses fewer nodes than a full tree while matching teacher performance more closely.