Multi-Objective Controller Synthesis with Uncertain Human Preferences
Multi-Objective Controller Synthesis with Uncertain Human Preferences
复制标题
DOI：
10.1109/iccps54341.2022.00022
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Shenghui Chen;Kayla Boggess;D. Parker;Lu Feng
中科院分区：
文献类型：
--
作者：
Shenghui Chen;Kayla Boggess;D. Parker;Lu Feng
网络物理系统的复杂实际应用产生了对多目标控制器综合的需求，这涉及到计算受多个（可能相互冲突的）标准约束的最优控制器的问题。目标的相对重要性通常由人类决策者指定。然而，人类偏好存在固有的不确定性（例如，由于不同偏好激发方法产生的人为因素）。在本文中，我们形式化了不确定人类偏好的概念，并提出了一种在马尔可夫决策过程（mdp）的多目标控制器综合背景下解释这种不确定性的新方法。我们的方法基于混合整数线性规划，并综合了一种最优允许的多策略，该策略满足了关于多目标特性的不确定人类偏好。一系列大型案例研究的实验结果表明，所提出的方法是可行的，并且可扩展到不同的MDP模型大小和人类偏好的不确定性水平。通过在线用户研究的评估也证明了合成控制器的质量和效益。
Complex real-world applications of cyber-physical systems give rise to the need for multi-objective controller synthesis, which con-cerns the problem of computing an optimal controller subject to multiple (possibly conflicting) criteria. The relative importance of objectives is often specified by human decision-makers. However, there is inherent uncertainty in human preferences (e.g., due to artifacts resulting from different preference elicitation methods). In this paper, we formalize the notion of uncertain human preferences, and present a novel approach that accounts for this uncertainty in the context of multi-objective controller synthesis for Markov decision processes (MDPs). Our approach is based on mixed-integer linear programming and synthesizes an optimally permissive multi-strategy that satisfies uncertain human preferences with respect to a multi-objective property. Experimental results on a range of large case studies show that the proposed approach is feasible and scalable across varying MDP model sizes and uncertainty levels of human preferences. Evaluation via an online user study also demon-strates the quality and benefits of the synthesized controllers.