Deep Spectral Q-learning with Application to Mobile Health
This work addresses personalized treatment optimization in mobile health, but it is incremental as it combines existing techniques like PCA and deep Q-learning for a specific data issue.
The authors tackled the challenge of handling mixed-frequency data in dynamic treatment regimes for mobile health by proposing deep spectral Q-learning, which integrates PCA with deep Q-learning, and demonstrated its effectiveness through simulations and a diabetes dataset application.
Dynamic treatment regimes assign personalized treatments to patients sequentially over time based on their baseline information and time-varying covariates. In mobile health applications, these covariates are typically collected at different frequencies over a long time horizon. In this paper, we propose a deep spectral Q-learning algorithm, which integrates principal component analysis (PCA) with deep Q-learning to handle the mixed frequency data. In theory, we prove that the mean return under the estimated optimal policy converges to that under the optimal one and establish its rate of convergence. The usefulness of our proposal is further illustrated via simulations and an application to a diabetes dataset.