English

dtControl2+$\varepsilon$: Trading Optimality for Explainability in MDPs via Decision Trees

Artificial Intelligence 2026-07-28 v1

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 "ε\varepsilon" functionality: Given an allowed imprecision ε0\varepsilon \geq 0, we construct a smaller decision tree, distilling the essence of the controller, while still guaranteeing its ε\varepsilon-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