Interpretable Skill Learning for Dynamic Treatment Regimes through Imitation
Imitation learning that mimics experts’ skills from their demonstrations has shown great success in discovering dynamic treatment regimes, i.e., the optimal decision rules to treat an individual patient based on related evolving treatment and covariate history. Existing imitation learning methods, however, still lack the capability to interpret the underlying rationales of the learned policy in a faithful way. Moreover, since dynamic treatment regimes for patients often exhibit varying patterns, i.e., symptoms that transit from one to another, the flat policy learned by a vanilla imitation learning method is typically undesired. To this end, we propose an Interpretable Skill Learning (ISL) framework to resolve the aforementioned challenges for dynamic treatment regimes through imitation. The key idea is to model each segment of experts’ demonstrations with a prototype layer and integrate it with the imitation learning layer to enhance the interpretation capability. On one hand, the ISL framework is able to provide interpretable explanations by matching the prototype to exemplar segments during the inference stage, which enables doctors to perform reasoning of the learned demonstrations based on human-understandable patient symptoms and lab results. On the other hand, the obtained skill embedding consisting of prototypes serves as conditional information to the imitation learning layer, which implicitly guides the policy network to provide a more accurate demonstration when the patients’ state switches from one stage to another. Thoroughly empirical studies demonstrate that our proposed ISL technique can achieve better performance than state-of-the-art methods. Moreover, the proposed ISL framework also exhibits good interpretability which cannot be observed in existing methods.