What question did this study set out to answer?

The study aims to systematically incorporate building decision-makers' preferences into reinforcement learning-based control systems.

May 10, 2026Indoor AirOpen Access

Reinforcement Learning–Based Building Control Considering Decision‐Makers′ Preferences Between Energy Use and Indoor Environmental Quality

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates user preference integration for energy efficiency in building control, suggesting improved outcomes.

The study aims to systematically incorporate building decision-makers' preferences into reinforcement learning-based control systems.
Analytic Hierarchy Process (AHP) was used to quantify user preferences.
K-means clustering categorized decision-maker preferences into five distinct types.
Reward weights for a double deep Q-network algorithm were assigned based on identified preference types.
Energy performance conscious model minimized energy use to 0.27 kWh while achieving a PMV of 1.88.
Thermal comfort conscious model provided a PMV of 0.12 but consumed 6.40 kWh.
The proposed approach successfully quantified decision-maker preferences for better building control.

Kim et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

May 10, 2026Indoor AirOpen Access

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial demonstrates user preference integration for energy efficiency in building control, suggesting improved outcomes.

The study aims to systematically incorporate building decision-makers' preferences into reinforcement learning-based control systems.
Analytic Hierarchy Process (AHP) was used to quantify user preferences.
K-means clustering categorized decision-maker preferences into five distinct types.
Reward weights for a double deep Q-network algorithm were assigned based on identified preference types.
Energy performance conscious model minimized energy use to 0.27 kWh while achieving a PMV of 1.88.
Thermal comfort conscious model provided a PMV of 0.12 but consumed 6.40 kWh.
The proposed approach successfully quantified decision-maker preferences for better building control.

Kim et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark