Extracting Expert's Goals by What-if Interpretable Modeling
Although reinforcement learning (RL) has tremendous success in many fields, applying RL to real-world settings such as healthcare is challenging when the reward is hard to specify and no exploration is allowed. In this work, we focus on recovering clinicians' rewards in treating patients. We incorporate the what-if reasoning to explain the clinician's treatments based on their potential future outcomes. We use generalized additive models (GAMs) - a class of accurate, interpretable models - to recover the reward. In both simulation and a real-world hospital dataset, we show our model outperforms baselines. Finally, our model's explanations match several clinical guidelines when treating patients while we found the commonly-used linear model often contradicts them.
Code (0)
등록된 구현이 없습니다.
Tasks
Additive modelsreinforcement-learningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Interpretable deep-learning models to help achieve the Sustainable Development Goals
We discuss our insights into interpretable artificial-intelligence (AI) models, and how they are essential in the context of developing ethical AI systems, as well as data-driven solutions compliant with the Sustainable …
Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations
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 dyna…
Decision MakingSchedulingLearning "What-if" Explanations for Sequential Decision-Making
Building interpretable parameterizations of real-world decision-making on the basis of demonstrated behavior -- i.e. trajectories of observations and actions made by an expert maximizing some unknown reward function -- i…
counterfactualCounterfactual ReasoningDecision Makingreinforcement-learning+3Counterfactual Probabilistic Diffusion with Expert Models
Predicting counterfactual distributions in complex dynamical systems is essential for scientific modeling and decision-making in domains such as public health and medicine. However, existing methods often rely on point e…
Causal InferenceThe FIX Benchmark: Extracting Features Interpretable to eXperts
Feature-based methods are commonly used to explain model predictions, but these methods often implicitly assume that interpretable features are readily available. However, this is often not the case for high-dimensional …
Time Series