用谓词决策图提升复杂控制器的可解释性。
Explaining Control Policies through Predicate Decision Diagrams
- 将决策树与二元决策图结合，引入谓词决策图新结构。
- 通过压缩技术构建更小的模型，提升可读性。
- 适合需要安全性和透明度的控制系统设计者。
复杂系统中的安全关键控制器难以手动构建。自动化方法如控制器合成或学习提供了替代方案，但通常缺乏可解释性。为此，学习型决策树（DTs）被广泛用于生成可解释的控制器模型。然而，决策树未利用共享决策机制，而这一概念在二元决策图（BDDs）中被用来减小规模并提升可解释性。本文提出谓词决策图（PDDs），在BDD基础上引入谓词，融合了决策树与二元决策图的优势，用于控制器表示。我们建立了一条高效的合成流程，从表示控制器的决策树构建PDDs，同时应用适用于BDD的压缩技术来优化PDDs。
原文摘要 · Abstract (English)
Safety-critical controllers of complex systems are hard to construct manually. Automated approaches such as controller synthesis or learning provide a tempting alternative but usually lack explainability. To this end, learning decision trees (DTs) have been prevalently used towards an interpretable model of the generated controllers. However, DTs do not exploit shared decision-making, a key concept exploited in binary decision diagrams (BDDs) to reduce their size and thus improve explainability. In this work, we introduce predicate decision diagrams (PDDs) that extend BDDs with predicates and thus unite the advantages of DTs and BDDs for controller representation. We establish a synthesis pipeline for efficient construction of PDDs from DTs representing controllers, exploiting reduction techniques for BDDs also for PDDs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。