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

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 had provided pipelines with tools supporting synthesis hybrid systems, such as and . We present , a new version several fundamentally novel features. Most importantly, user can now provide domain knowledge to be exploited in tree learning process interactively steer based on dynamically information. To this end, we graphical interface. It allows inspection re-computation of parts result, suggesting well receiving advice predicates, visual simulation decision-making process. Besides, interface model checkers probabilistic namely dedicated support categorical enumeration-type state variables. Consequently, controllers explainable smaller.