Did we personalize? Assessing personalization by an online reinforcement learning algorithm using resampling
This work addresses the need for reliable evaluation of personalization in RL algorithms for digital health, which is crucial for ensuring effective real-world deployment, though it is incremental as it builds on existing RL and resampling techniques.
The paper tackles the problem of verifying whether an online reinforcement learning algorithm genuinely personalizes treatments in digital health interventions, by introducing a resampling-based methodology to assess if observed personalization is due to algorithm stochasticity, and demonstrates its application in a physical activity clinical trial called HeartSteps.
There is a growing interest in using reinforcement learning (RL) to personalize sequences of treatments in digital health to support users in adopting healthier behaviors. Such sequential decision-making problems involve decisions about when to treat and how to treat based on the user's context (e.g., prior activity level, location, etc.). Online RL is a promising data-driven approach for this problem as it learns based on each user's historical responses and uses that knowledge to personalize these decisions. However, to decide whether the RL algorithm should be included in an ``optimized'' intervention for real-world deployment, we must assess the data evidence indicating that the RL algorithm is actually personalizing the treatments to its users. Due to the stochasticity in the RL algorithm, one may get a false impression that it is learning in certain states and using this learning to provide specific treatments. We use a working definition of personalization and introduce a resampling-based methodology for investigating whether the personalization exhibited by the RL algorithm is an artifact of the RL algorithm stochasticity. We illustrate our methodology with a case study by analyzing the data from a physical activity clinical trial called HeartSteps, which included the use of an online RL algorithm. We demonstrate how our approach enhances data-driven truth-in-advertising of algorithm personalization both across all users as well as within specific users in the study.