dtControl2+$\varepsilon$: Trading Optimality for Explainability in MDPs via Decision Trees
Abstract
Over the past decade, decision trees have been used to represent controllers (a.k.a. policies) in an explainable way, with dtControl2 as a current state-of-the-art tool. However, for systems that are large or have many corner cases, even such representations tend to be too complex and not human-comprehensible. Unfortunately, reducing the size of the decision tree is not straightforward, as missing just a single crucial case might result in an incorrect controller. We tackle this issue in the setting of Markov decision processes, extending dtControl2 by "" functionality: Given an allowed imprecision , we construct a smaller decision tree, distilling the essence of the controller, while still guaranteeing its -optimality. This enables us to provide tunably simpler explanations, omitting a controllable amount of detail. Our tool constructs decision trees that are orders of magnitude smaller than the state of the art.
Cite
@article{arxiv.2607.25925,
title = {dtControl2+$\varepsilon$: Trading Optimality for Explainability in MDPs via Decision Trees},
author = {Tereza Kinská and Jan Křetínský and Tobias Meggendorfer and Sabine Rieder and Maximilian Weininger},
journal= {arXiv preprint arXiv:2607.25925},
year = {2026}
}
Comments
This paper is accepted at FMCAD26