dtControl2+ε: Trading Optimality for Explainability in MDPs via Decision Trees

Le résumé fourni par la source

Over the past decade, decision trees have been used to represent controllers (a.k.a. policies) in an explainable way, with dtControl 2 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 dtControl 2 by “ε” functionality: Given an allowed imprecision ε ≥ 0, we construct a smaller decision tree, distilling the essence of the controller, while still guaranteeing its ε-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.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.