Resource scheduling and coordination is an NP-hard optimization requiring an efficient allocation of agents to a set of tasks with upper-and lower bound temporal and resource constraints. Due to the large-scale and dynamic nature of resource coordination in hospitals and factories, human domain experts manually plan and adjust schedules on the fly. To perform this job, domain experts leverage heterogeneous strategies and rules-of-thumb honed over years of apprenticeship. What is critically needed is the ability to extract this domain knowledge in a heterogeneous and interpretable apprenticeship learning framework to scale beyond the power of a single human expert, a necessity in safety-critical domains. We propose a personalized and interpretable apprenticeship scheduling algorithm that infers an interpretable representation of all human task demonstrators by extracting decision-making criteria via an inferred, personalized embedding non-parametric in the number of demonstrator types. We achieve near-perfect LfD accuracy in synthetic domains and 88.22\% accuracy on a planning domain with real-world data, outperforming baselines. Finally, our user study showed our methodology produces more interpretable and easier-to-use models than neural networks ($p < 0.05$).

Weaknesses: A major point of concern is the value of the user study in comparing the interpretability of the scheduling decision tree to that of a neural network. While there is nothing wrong with the study methodology itself, or subsequent statistical analysis, it is not clear that the user study is really capturing the difference in interpretability between the neural network and the decision tree. IT seems that the study may not really be testing the hypotheses (H1, H2, H3) that the authors claim it is. The study asks participants to manually compute the outputs of decision trees and neural networks, given their decision thresholds (for trees) or weights and biases (for networks). It is not surprising that it is easier to manually execute a decision tree, as many fewer operations are needed, but this question seems spurious. In practice, we would never expect a user to manually compute the output of a neural network (or a large decision tree for that matter).

Resource scheduling and coordination is an NP-hard optimization requiring an efficient allocation of agents to a set of tasks with upper- and lower bound temporal and resource constraints. Due to the large-scale and dynamic nature of resource coordination in hospitals and factories, human domain experts manually plan and adjust schedules on the fly. To perform this job, domain experts leverage heterogeneous strategies and rules-of-thumb honed over years of apprenticeship. What is critically needed is the ability to extract this domain knowledge in a heterogeneous and interpretable apprenticeship learning framework to scale beyond the power of a single human expert, a necessity in safety-critical domains. We propose a personalized and interpretable apprenticeship scheduling algorithm that infers an interpretable representation of all human task demonstrators by extracting decision-making criteria via an inferred, personalized embedding non-parametric in the number of demonstrator types.