Iterative Oblique Decision Trees Deliver Explainable RL Models

Iterative Oblique Decision Trees Deliver Explainable RL Models

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 in...

Full description

Bibliographic Details
Main Authors: Raphael C. Engelhardt, Marc Oedingen, Moritz Lange, Laurenz Wiskott, Wolfgang Konen
Format: Article
Language:English
Published: MDPI AG 2023-05-01
Series:Algorithms
Subjects:
reinforcement learning
decision tree
explainable AI
rule learning
Online Access:https://www.mdpi.com/1999-4893/16/6/282

Internet

https://www.mdpi.com/1999-4893/16/6/282

Similar Items