Extracting Expert's Goals by What-if Interpretable Modeling

2021/10/28 by Chun‐Hao Chang, George Alexandru Adam, Chang, Chun-Hao +5
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Healthcare

paper · pdf · doi:10.48550/arxiv.2110.15165

openalex publication_date 2021/10/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Related

• Challenges for Reinforcement Learning in Healthcare
• Decision-Focused Model-based Reinforcement Learning for Reward Transfer
• Clinician-in-the-Loop Decision Making: Reinforcement Learning with\n Near-Optimal Set-Valued Policies
• Evaluating Reinforcement Learning Algorithms in Observational Health Settings
• Learning "What-if" Explanations for Sequential Decision-Making