Each week, we select a recently published Open Access article to feature. This week’s article comes from from Stat and proposes a deep spectral Q-learning algorithm. 

The article’s abstract is given below, with the full article available to read here.

Gao, Y., Shi, C., & Song, R. (2023). Deep spectral Q-learning with application to mobile health. Stat, 12( 1), e564. https://doi.org/10.1002/sta4.564

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.