Search Results for author:
Found 7 papers, 0 papers with code
Stage-Aware Learning for Dynamic Treatments
In particular, the proposed learning scheme builds a more general framework which includes the popular outcome weighted learning framework as a special case of ours.
Stackelberg Batch Policy Learning
From a theoretical standpoint, we provide instance-dependent regret bounds with general function approximation, which shows that our algorithm can learn a best-effort policy that is able to compete against any comparator policy that is covered by batch data.
A Model-Agnostic Graph Neural Network for Integrating Local and Global Information
Graph Neural Networks (GNNs) have achieved promising performance in a variety of graph-focused tasks.
Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework
This task faces two primary challenges: providing a comprehensive and rigorous error quantification in CI estimation, and addressing the distributional shift that results from discrepancies between the distribution induced by the target policy and the offline data-generating process.
Quasi-optimal Reinforcement Learning with Continuous Actions
Many real-world applications of reinforcement learning (RL) require making decisions in continuous action environments.
Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning
To address these challenges, we propose a Proximal Temporal consistency Learning (pT-Learning) framework to estimate an optimal regime that is adaptively adjusted between deterministic and stochastic sparse policy models.
Multicategory Angle-based Learning for Estimating Optimal Dynamic Treatment Regimes with Censored Data
An optimal dynamic treatment regime (DTR) consists of a sequence of decision rules in maximizing long-term benefits, which is applicable for chronic diseases such as HIV infection or cancer.
