发表机构
College of Information and Electrical Engineering, China Agricultural University（中国农业大学信息与电气工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对智能温室控制，提出校准优先奖励审计框架，在GreenLight - Gym中分解标量奖励，使其适应气候轨迹并对温室数据组件评分，确保奖励组件在多场景下可比。
AI 中文摘要
温室强化学习能够以单独作物实验难以达到的速度和规模测试气候控制理念。然而对于智能温室控制，单一模拟器回报是不够的。本文提出了一个可重复的校准优先奖励审计框架，该框架能使温室控制奖励组件在模拟器训练、设施适配部署、记录的自主温室挑战记录及执行器规则提炼中保持可比。在GreenLight - Gym中，该框架将标量奖励分解为条件温度、二氧化碳、湿度等项，使GreenLight适应第二次自主温室挑战记录的气候轨迹，并对记录的温室数据中的相同组件进行评分。
英文摘要
Greenhouse reinforcement learning can test climate-control ideas at a speed and scale that is difficult to achieve with crop experiments alone. For smart-greenhouse control, however, a single simulator return is not enough: a grower or control engineer also needs to know when the policy heats, enriches CO2, vents, manages humidity, deploys screens, or uses lamps.We propose a reproducible calibration-first reward audit framework that keeps named greenhouse-control reward components comparable across simulator training, facility-adapted rollouts, logged Autonomous Greenhouse Challenge records, and actuator-rule distillation. In GreenLight-Gym, the framework decomposes the scalar reward into conditional temperature, CO2, humidity and vapor-pressure-deficit, screen, and actuation-proxy terms; adapts GreenLight to the second Autonomous Greenhouse Challenge logged climate traces; and scores the same components on logged greenhouse data.
Comments28 pages, 8 figures
