dtControl 2.0: Explainable Strategy Representation via Decision Tree Learning Steered by Experts
This work addresses the need for explainable strategy synthesis in hybrid and probabilistic systems, offering incremental improvements through interactive features and domain-specific support.
The authors tackled the problem of representing strategies for hybrid and probabilistic systems more explainably and concisely by introducing dtControl 2.0, which allows users to incorporate domain knowledge and interactively steer decision tree learning, resulting in more explainable and smaller controllers.
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.