Interpretability of AI models allows for user safety checks to build trust in such AIs. In particular, Decision Trees (DTs) provide a global look at the learned model and transparently reveal which features of the input are critical for making a decision. However, interpretability is hindered if the DT is too large. To learn compact trees, a recent Reinforcement Learning (RL) framework has been proposed to explore the space of DTs using deep RL. This framework augments a decision problem (e.g. a supervised classification task) with additional actions that gather information about the features of an otherwise hidden input. By appropriately penalizing these actions, the agent learns to optimally trade-off size and performance of DTs. In practice, a reactive policy for a partially observable Markov decision process (MDP) needs to be learned, which is still an open problem. We show in this paper that deep RL can fail even on simple toy tasks of this class. However, when the underlying decision problem is a supervised classification task, we show that finding the optimal tree can be cast as a fully observable Markov decision problem and be solved efficiently, giving rise to a new family of algorithms for learning DTs that go beyond the classical greedy maximization ones.

翻译：AI模型的可解释性允许用户进行安全检查，从而建立对此类AI的信任。特别是，决策树（DTs）提供了对学习模型的全局视角，并透明地揭示输入中的哪些特征对于做出决策至关重要。然而，如果决策树过大，其可解释性就会受到阻碍。为了学习紧凑的决策树，最近提出了一种强化学习（RL）框架，利用深度强化学习探索决策树空间。该框架通过增加额外动作来收集关于原本隐藏输入特征的信息，从而增强决策问题（例如监督分类任务）。通过适当惩罚这些动作，智能体学会在决策树的大小与性能之间进行最优权衡。实际上，需要学习一个针对部分可观测马尔可夫决策过程（MDP）的反应性策略，这仍然是一个开放问题。本文表明，即使在此类任务的简单玩具示例上，深度强化学习也可能失败。然而，当底层决策问题是监督分类任务时，我们证明寻找最优决策树可以转化为完全可观测的马尔可夫决策问题，并得到高效求解，从而催生了一类超越传统贪婪最大化方法的学习决策树新算法家族。