OccuReward: 面向电网交互建筑中人口公平性的LLM引导的以 occupant 为中心的奖励塑造
OccuReward: LLM-Guided Occupant-Centric Reward Shaping for Demographic Equity in Grid-Interactive Buildings
AI总结：
提出OccuReward框架，利用大语言模型迭代塑造奖励函数，通过舒适公平指数(CEI)反馈，在CityLearn v2中提升不同人口群体的舒适公平性，同时降低能耗成本。
摘要：
大语言模型（LLM）在为基于深度强化学习（DRL）的建筑能源管理生成奖励函数方面展现出有前景的能力。然而，它们在异质人口群体中引发或加剧 occupant 舒适度差异的潜力尚未被探索。我们提出 OccuReward，一个研究 LLM 介导的奖励设计如何影响人口公平性的框架。我们的贡献有三方面：引入舒适公平指数（CEI）作为新颖的反馈信号；一种迭代的、公平感知的 LLM 奖励塑造方法；以及在这些优化目标下 DRL 代理的性能分析。利用来自 ASHRAE 全球热舒适数据库 II（13,440 票）的四个基于经验 occupant 档案，我们在 CityLearn v2 中部署了一个 Soft Actor-Critic 代理。我们的方法使用 Gemini API 生成奖励函数逻辑和权重——而不是执行每步推理——跨越三个细化轮次。15 个实验运行的结果显示，老年女性 occupant 在初始轮次中始终经历最低满意度。到第 3 轮，公平感知的 LLM 细化激活了特定的奖励组件，提高了年轻男性（+17.6%）、中年女性（+28.2%）、健康敏感者（+53.8%）和老年女性（+567%）的满意度，同时降低了 3.2% 的能源成本。我们的发现强调，虽然奖励层面的干预显著改善了公平性，但 AI 驱动控制器中的人口差异仍然存在，需要进一步研究建筑系统中的算法公平性。
英文摘要：
Large language models (LLMs) have demonstrated promising capability in generating reward functions for deep reinforcement learning (DRL)-based building energy management. However, their potential to exhibit or exacerbate disparities in occupant comfort across heterogeneous demographic populations remains unexplored. We present OccuReward, a framework investigating how LLM-mediated reward design affects demographic equity. Our contribution is three-fold: the introduction of the Comfort Equity Index (CEI) as a novel feedback signal; a methodology for iterative, equity-aware LLM reward shaping; and a performance analysis of DRL agents under these refined objectives. Utilizing four empirically grounded occupant profiles from the ASHRAE Global Thermal Comfort Database II (13,440 votes), we deploy a Soft Actor-Critic agent in CityLearn v2. Our approach employs the Gemini API to generate reward function logic and weights--rather than performing per-step inference--across three refinement rounds. Results across 15 experimental runs reveal that elderly female occupants consistently experience the lowest satisfaction in initial rounds. By Round 3, equity-aware LLM refinement activates specific reward components that improve satisfaction for Young Males (+17.6%), Mid-aged Females (+28.2%), Health Sensitive (+53.8%), and Elderly Females (+567%), while simultaneously reducing energy costs by 3.2%. Our findings highlight that while reward-level intervention significantly improves equity, demographic disparities in AI-driven controllers persist, necessitating further research into algorithmic fairness in building systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
