2020/11/15 by Zihan Ding, Pablo Hernández-Leal, Ding, Zihan +8 · 11 citations
Computer Science · Mathematics · #Adversarial Robustness in Machine Learning #Artificial intelligence #Black box #Computer science #Decision tree #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Function (biology) #Imitation #Machine Learning (cs.LG) #Machine learning #Mathematics #Reinforcement Learning in Robotics #Reinforcement learning #Representation (politics) #Tree (set theory) #cs.LG
paper · pdf · doi:10.48550/arxiv.2011.07553
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2020/11/15 · arxiv created 2021/03/30 · arxiv updated 2021/03/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Deep Reinforcement Learning (DRL) has recently achieved significant advances in various domains. However, explaining the policy of RL agents still remains an open problem due to several factors, one being the complexity of explaining neural networks decisions. Recently, a group of works have used decision-tree-based models to learn explainable policies. Soft decision trees (SDTs) and discretized differentiable decision trees (DDTs) have been demonstrated to achieve both good performance and share the benefit of having explainable policies. In this work, we further improve the results for tree-based explainable RL in both performance and explainability. Our proposal, Cascading Decision Trees (CDTs) apply representation learning on the decision path to allow richer expressivity. Empirical results show that in both situations, where CDTs are used as policy function approximators or as imitation learners to explain black-box policies, CDTs can achieve better performances with more succinct and explainable models than SDTs. As a second contribution our study reveals limitations of explaining black-box policies via imitation learning with tree-based explainable models, due to its inherent instability.