dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by Experts

TL;DR

dtControl 2.0 enhances explainable strategy representation by integrating expert domain knowledge and interactive steering in decision tree learning, supported by a graphical interface and probabilistic model checkers, resulting in more concise and understandable controllers.

Contribution

It introduces a novel interactive decision tree learning framework with expert input and visualization, improving strategy explainability and efficiency in hybrid systems.

Findings

Controllers are more explainable and smaller.

Interactive steering improves strategy synthesis.

Integration with probabilistic model checkers enhances applicability.

Abstract

Recent advances have shown how decision trees are apt data structures for concisely representing strategies (or controllers) satisfying various objectives. Moreover, they also make the strategy more explainable. The recent tool dtControl had provided pipelines with tools supporting strategy synthesis for hybrid systems, such as SCOTS and Uppaal Stratego. We present dtControl 2.0, a new version with several fundamentally novel features. Most importantly, the user can now provide domain knowledge to be exploited in the decision tree learning process and can also interactively steer the process based on the dynamically provided information. To this end, we also provide a graphical user interface. It allows for inspection and re-computation of parts of the result, suggesting as well as receiving advice on predicates, and visual simulation of the decision-making process. Besides, we interface model checkers of probabilistic systems, namely Storm and PRISM and provide dedicated support for categorical enumeration-type state variables. Consequently, the controllers are more explainable and smaller.