# Policy Optimization for Personalized Interventions in Behavioral Health

arXiv: https://arxiv.org/abs/2303.12206 · HTML: https://mlsanity.com/paper/2303.12206/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 49 references that are in the map.
- First posted on arXiv 21 Mar 2023.

## Builds on (most cited first, 12 of 12)

- [Is Q-learning Provably Efficient?](https://mlsanity.com/paper/1807.03765/) (2018)
- [Offline RL Without Off-Policy Evaluation](https://mlsanity.com/paper/2106.08909/) (2021)
- [What are the Statistical Limits of Offline RL with Linear Function Approximation?](https://mlsanity.com/paper/2010.11895/) (2020)
- [Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity](https://mlsanity.com/paper/1909.03539/) (2019)
- [Collapsing Bandits and Their Application to Public Health Interventions](https://mlsanity.com/paper/2007.04432/) (2020)
- [Whittle index based Q-learning for restless bandits with average reward](https://mlsanity.com/paper/2004.14427/) (2020)
- [Field Study in Deploying Restless Multi-Armed Bandits: Assisting Non-Profits in Improving Maternal and Child Health](https://mlsanity.com/paper/2109.08075/) (2021)
- [Learn to Intervene: An Adaptive Learning Policy for Restless Bandits in Application to Preventive Healthcare](https://mlsanity.com/paper/2105.07965/) (2021)
- [Regret Bounds for Thompson Sampling in Episodic Restless Bandit Problems](https://mlsanity.com/paper/1905.12673/) (2019)
- [Restless-UCB, an Efficient and Low-complexity Algorithm for Online Restless Bandits](https://mlsanity.com/paper/2011.02664/) (2020)
- [Non-Stationary Bandits with Habituation and Recovery Dynamics](https://mlsanity.com/paper/1707.08423/) (2017)
- [An Actor-Critic Contextual Bandit Algorithm for Personalized Mobile Health Interventions](https://mlsanity.com/paper/1706.09090/) (2017)

## Built on by (most cited first, 9 of 9)

- [Designing Algorithmic Recommendations to Achieve Human-AI Complementarity](https://mlsanity.com/paper/2405.01484/) (2024)
- [The Digital Transformation in Health: How AI Can Improve the Performance of Health Systems](https://mlsanity.com/paper/2409.16098/) (2024)
- [Power Constrained Nonstationary Bandits with Habituation and Recovery Dynamics](https://mlsanity.com/paper/2511.02944/) (2025)
- [On the Limited Representational Power of Value Functions and its Links to Statistical (In)Efficiency](https://mlsanity.com/paper/2403.07136/) (2024)
- [Optimizing HIV Patient Engagement with Reinforcement Learning in Resource-Limited Settings](https://mlsanity.com/paper/2408.07629/) (2024)
- [Adaptive User Journeys in Pharma E-Commerce with Reinforcement Learning: Insights from SwipeRx](https://mlsanity.com/paper/2408.08024/) (2024)
- [Multi-agent Markov Entanglement](https://mlsanity.com/paper/2506.02385/) (2025)
- [Deployment of AI-Assisted Interventions: Capacity Constraints and Noisy Compliance](https://mlsanity.com/paper/2604.14370/) (2026)
- [Optimizing Digital Therapeutic Interventions: Online Learning under Endogenous Adherence](https://mlsanity.com/paper/2605.24261/) (2026)

## Abstract (arXiv)

Behavioral health interventions, delivered through digital platforms, have the potential to significantly improve health outcomes, through education, motivation, reminders, and outreach. We study the problem of optimizing personalized interventions for patients to maximize a long-term outcome, where interventions are costly and capacity-constrained. We assume we have access to a historical dataset collected from an initial pilot study. We present a new approach for this problem that we dub DecompPI, which decomposes the state space for a system of patients to the individual level and then approximates one step of policy iteration. Implementing DecompPI simply consists of a prediction task using the dataset, alleviating the need for online experimentation. DecompPI is a generic model-free algorithm that can be used irrespective of the underlying patient behavior model. We derive theoretical guarantees on a simple, special case of the model that is representative of our problem setting. When the initial policy used to collect the data is randomized, we establish an approximation guarantee for DecompPI with respect to the improvement beyond a null policy that does not allocate interventions. We show that this guarantee is robust to estimation errors. We then conduct a rigorous empirical case study using real-world data from a mobile health platform for improving treatment adherence for tuberculosis. Using a validated simulation model, we demonstrate that DecompPI can provide the same efficacy as the status quo approach with approximately half the capacity of interventions. DecompPI is simple and easy to implement for an organization aiming to improve long-term behavior through targeted interventions, and this paper demonstrates its strong performance both theoretically and empirically, particularly in resource-limited settings.