paper-with-me

홈 › Papers

Extracting Expert's Goals by What-if Interpretable Modeling

2021-10-28 · Chun-Hao Chang, George Alexandru Adam, Rich Caruana, Anna Goldenberg

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.

📄 PDF Abstract BibTeX arXiv:2110.15165

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

2021-08-24 · Ricardo Vinuesa, Beril Sirmacek

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

2019-06-14 · NeurIPS 2020 12 · Rohan Paleja, Andrew Silva, Letian Chen, Matthew Gombolay

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 MakingScheduling

Learning "What-if" Explanations for Sequential Decision-Making

2020-07-02 · ICLR 2021 1 · Ioana Bica, Daniel Jarrett, Alihan Hüyük, Mihaela Van Der Schaar

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+3

Counterfactual Probabilistic Diffusion with Expert Models

2025-08-18 · Wenhao Mu, Zhi Cao, Mehmed Uludag, Alexander Rodríguez arxiv

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 Inference

The FIX Benchmark: Extracting Features Interpretable to eXperts

2024-09-20 · Helen Jin, Shreya Havaldar, Chaehyeon Kim, Anton Xue 외

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