EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Iterative Oblique Decision Trees Deliver Explainable RL Models

Raphael C. Engelhardt, Marc Oedingen, Moritz Lange, Laurenz Wiskott, Wolfgang Konen

Algorithms · 31.05.2023 · 16 (6) · 282

DOI: 10.3390/a16060282 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Algorithms, online erschienen am 31.05.2023. Verfasst von Raphael C. Engelhardt und 4 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: German federal state of North Rhine-Westphalia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The demand for explainable and transparent models increases with the continued success of reinforcement learning. In this article, we explore the potential of generating shallow decision trees (DTs) as simple and transparent surrogate models for opaque deep reinforcement learning (DRL) agents. We investigate three algorithms for generating training data for axis-parallel and oblique DTs with the help of DRL agents (“oracles”) and evaluate these methods on classic control problems from OpenAI Gym. The results show that one of our newly developed algorithms, the iterative training, outperforms traditional sampling algorithms, resulting in well-performing DTs that often even surpass the oracle from which they were trained. Even higher dimensional problems can be solved with surprisingly shallow DTs. We discuss the advantages and disadvantages of different sampling methods and insights into the decision-making process made possible by the transparent nature of DTs. Our work contributes to the development of not only powerful but also explainable RL agents and highlights the potential of DTs as a simple and effective alternative to complex DRL models.

Förderung

  • German federal state of North Rhine-Westphalia

Zitieren

APA

Engelhardt, R. C., Oedingen, M., Lange, M., Wiskott, L., & Konen, W. (2023). Iterative Oblique Decision Trees Deliver Explainable RL Models. Algorithms, 16(6), 282. https://doi.org/10.3390/a16060282

Vancouver

Engelhardt RC, Oedingen M, Lange M, Wiskott L, Konen W. Iterative Oblique Decision Trees Deliver Explainable RL Models. Algorithms. 2023;16(6):282. doi:10.3390/a16060282

BibTeX
@article{Engelhardt2023,
  author = {Engelhardt, Raphael C. and Oedingen, Marc and Lange, Moritz and Wiskott, Laurenz and Konen, Wolfgang},
  title = {Iterative Oblique Decision Trees Deliver Explainable RL Models},
  journal = {Algorithms},
  year = {2023},
  volume = {16},
  number = {6},
  pages = {282},
  doi = {10.3390/a16060282}
}
Kostenlos starten →