Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment Settings

TL;DR

This paper introduces a deep jump learning approach for off-policy evaluation in continuous treatment settings, enabling adaptive discretization of treatment space to improve estimation accuracy in personalized dose-finding.

Contribution

It proposes a novel deep discretization method for continuous treatments, bridging the gap between discrete OPE techniques and continuous treatment applications.

Findings

Effective discretization of continuous treatments using deep learning.

Theoretical guarantees for the proposed estimation method.

Successful application to Warfarin Dosing data.

Abstract

We consider off-policy evaluation (OPE) in continuous treatment settings, such as personalized dose-finding. In OPE, one aims to estimate the mean outcome under a new treatment decision rule using historical data generated by a different decision rule. Most existing works on OPE focus on discrete treatment settings. To handle continuous treatments, we develop a novel estimation method for OPE using deep jump learning. The key ingredient of our method lies in adaptively discretizing the treatment space using deep discretization, by leveraging deep learning and multi-scale change point detection. This allows us to apply existing OPE methods in discrete treatments to handle continuous treatments. Our method is further justified by theoretical results, simulations, and a real application to Warfarin Dosing.