使用黑盒强化学习实现分类树的最佳可解释性与性能平衡（英文版）

英文标题：Optimal Interpretability-Performance Trade-off of Classification Trees with Black-Box Reinforcement Learning中文摘要：该论文研究了一种新的 Reinforcement Learning (RL) 框架，证明了只需要解决一个完全可观测的问题就能学习到一个优化可解释性 - 性能平衡的决策树。英文摘要：Interpretability of AI models allows for user safety checks to build trust inthese models. In particular, decision trees (DTs) provide a global view on thelearned model and clearly outlines the role of the features that are criticalto classify a given data. However, interpretability is hind