Reimagining service delivery in the agentic era with Google Public Sector
cloud.google.com·23h ago
AI Research
arXiv CS.AI·May 28·8 min read
OccuReward: LLM-Guided Occupant-Centric Reward Shaping for Demographic Equity in Grid-Interactive Buildings
TL;DR
Smart buildings that respond to electrical grid demands often optimize for energy efficiency rather than occupant comfort, creating inequitable outcomes across demographic groups. OccuReward uses large language models (LLMs) to automatically shape reward functions—the numerical signals that guide AI decision-making—to prioritize occupant well-being alongside grid responsiveness.
✦ Why It Matters
Engineers can use LLM-guided reward shaping to embed fairness into building automation systems without manual policy redesign.
Key Takeaways
- Utilize LLMs for designing reward functions in energy management.
- Incorporate the Comfort Equity Index for better feedback.
- Refine reward functions iteratively to improve occupant satisfaction.
- Focus on demographic equity to reduce disparities in comfort.
How It Works
OccuReward employs large language models to generate reward functions that prioritize occupant comfort across diverse demographic profiles. By analyzing feedback through the Comfort Equity Index, the framework iteratively refines these functions, ensuring that improvements in satisfaction are equitable among different groups.