Evaluating Heuristics in Engineering Design: A Reinforcement Learning Approach
Evaluating Heuristics in Engineering Design: A Reinforcement Learning Approach
复制标题
评估工程设计中的启发式方法：强化学习方法
DOI：
10.1115/detc2021-70425
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Panchal, Jitesh H.
中科院分区：
文献类型：
--
作者：
ElSayed, Karim A.;Bilionis, Ilias;Panchal, Jitesh H.
启发式对于解决工程设计过程的复杂性至关重要。逻辑学的优点取决于上下文。恰当的定制策略可以使设计师有效地找到好的解决方案，而不恰当的策略会导致认知偏差和低劣的设计结果。虽然已经有几个努力在理解设计师使用的是哪一种方法，但对于何时适合不同的方法缺乏规范性的理解。为了解决这一差距，本文提出了一种基于强化学习的方法来评估设计师通常面临的三个子问题的性能：（1）学习设计空间和性能空间之间的映射，（2）获取顺序信息，（3）停止信息获取过程。使用多臂强盗制定和仿真研究，我们学习这些单独的子问题在不同的资源约束和问题的复杂性合适的算法。此外，我们学习了组合问题的最优算法（即，一个组成所有三个子问题），我们将它们与在子问题层面上学习的内容进行比较。我们的模拟研究的结果表明，所提出的基于强化学习的方法可以有效地确定不同问题的策略的质量，以及策略的有效性如何根据设计者的偏好（例如，性能与成本）、问题的复杂性以及可用资源。
Heuristics are essential for addressing the complexities of engineering design processes. The goodness of heuristics is context-dependent. Appropriately tailored heuristics can enable designers to find good solutions efficiently, and inappropriate heuristics can result in cognitive biases and inferior design outcomes. While there have been several efforts at understanding which heuristics are used by designers, there is a lack of normative understanding about when different heuristics are suitable. Towards addressing this gap, this paper presents a reinforcement learning-based approach to evaluate the goodness of heuristics for three sub-problems commonly faced by designers: (1) learning the map between the design space and the performance space, (2) acquiring sequential information, and (3) stopping the information acquisition process. Using a multi-armed bandit formulation and simulation studies, we learn the suitable heuristics for these individual sub-problems under different resource constraints and problem complexities. Additionally, we learn the optimal heuristics for the combined problem (i.e., the one composing all three sub-problems), and we compare them to ones learned at the sub-problem level. The results of our simulation study indicate that the proposed reinforcement learning-based approach can be effective for determining the quality of heuristics for different problems, and how the effectiveness of the heuristics changes as a function of the designer’s preference (e.g., performance versus cost), the complexity of the problem, and the resources available.