因子化调度原理：通过结构化加性函数学习可解释且可迁移的策略
Factorized Scheduling Principle: Learning Interpretable and Transferable Policies via Structured Additive Functions
- Sejong University（世宗大学）
- Artificial Intelligence Robotics Institute (AIRI), Sejong University（世宗大学人工智能机器人研究所（AIRI））
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出因子化调度原理框架，将调度策略分解为加性分量，学习可解释且可迁移的规则，并在合成和现实任务中验证了性能与零样本泛化能力。
AI中文摘要：
调度问题源于根据候选对象的状态从一组候选中重复选择一项。这些问题通常简化为分配优先级分数并选择排名最高的项。在本工作中，我们提出了一种因子化调度原理（FSP）框架，用于学习可解释且可迁移的调度规则。FSP框架将系统状态表示为条件分布，并将全局调度原理分解为具有可辨识性约束的加性单变量和成对分量。该调度原理使框架在部署期间能够保持基于优先级的简单结构。该原理通过使用基于策略的目标结合定义在条件分布上的时间差分信号来学习。在合成和现实调度任务上的实验表明，FSP框架具有强大的性能、可解释性以及在不同系统规模上的零样本泛化能力。
英文摘要：
Scheduling problems arise from repeatedly selecting one item from a set of candidates based on their states. These problems often reduce to assigning priority scores and choosing the highest-ranked item. In this work, we propose a factorized scheduling principle (FSP) framework to learn interpretable and transferable scheduling rules. The FSP framework represents system states as condition distributions and decomposes a global scheduling principle into additive univariate and pairwise components with identifiability constraints. The scheduling principle enables the framework to maintain a simple priority-based structure during deployment. This principle is learned by using a policy-based objective combined with a temporal-difference signal defined on the condition distribution. Experiments on synthetic and realistic scheduling tasks demonstrate the FSP framework's strong performance, interpretability, and zero-shot generalization across different system scales.
