Options framework is one of the prominent models serving as a basis to improve learning speed by means of temporal abstractions. An option is mainly composed of three elements: initiation set, option’s local policy and termination condition. Although various attempts exist that focus on how to derive high-quality termination conditions for a given problem, the impact of initiation set generation is relatively unexplored. In this work, we propose an effective goal-oriented heuristic method to derive useful initiation set elements via an analysis of the recent history of events. Effectiveness of the method is experimented on various benchmark problems, and the results are discussed.

中文翻译：

---

为子目标驱动的选项生成有效的启动集

选项框架是突出的模型之一，可作为通过时间抽象提高学习速度的基础。一个选项主要由三个元素组成：启动集、选项的本地策略和终止条件。尽管存在各种尝试，专注于如何为给定问题推导高质量的终止条件，但初始集生成的影响相对而言尚未得到探索。在这项工作中，我们提出了一种有效的面向目标的启发式方法，通过分析最近的事件历史来推导出有用的启动集元素。在各种基准问题上对该方法的有效性进行了实验，并对结果进行了讨论。