# Dynamic Treatment on Networks

arXiv: https://arxiv.org/abs/2605.06564 · HTML: https://mlsanity.com/paper/2605.06564/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 46 references that are in the map.
- First posted on arXiv 7 May 2026.

## Builds on (most cited first, 14 of 14)

- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Is Pessimism Provably Efficient for Offline RL?](https://mlsanity.com/paper/2012.15085/) (2020)
- [d3rlpy: An Offline Deep Reinforcement Learning Library](https://mlsanity.com/paper/2111.03788/) (2021)
- [Collapsing Bandits and Their Application to Public Health Interventions](https://mlsanity.com/paper/2007.04432/) (2020)
- [Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks](https://mlsanity.com/paper/2010.05313/) (2020)
- [Influence Maximization with Bandits](https://mlsanity.com/paper/1503.00024/) (2015)
- [Policy Targeting under Network Interference](https://mlsanity.com/paper/1906.10258/) (2019)
- [Fair Policy Targeting](https://mlsanity.com/paper/2005.12395/) (2020)
- [Networked Restless Multi-Armed Bandits for Mobile Interventions](https://mlsanity.com/paper/2201.12408/) (2022)
- [Networked Restless Bandits with Positive Externalities](https://mlsanity.com/paper/2212.05144/) (2022)
- [Influence Maximization via Graph Neural Bandits](https://mlsanity.com/paper/2406.12835/) (2024)
- [Scalable Policy Maximization Under Network Interference](https://mlsanity.com/paper/2505.18118/) (2025)
- [Optimal Targeting in Dynamic Systems](https://mlsanity.com/paper/2507.00312/) (2025)

## Abstract (arXiv)

In networks, effective dynamic treatment allocation requires deciding both whom to treat and also when, so as to amplify policy impact through spillovers. An early intervention at a well-connected node can trigger cascades that change which nodes are worth targeting in the next period. Existing treatment strategies under network interference are largely static while dynamic treatment frameworks typically ignore network structure altogether. We integrate these perspectives and propose Q-Ising, a three-stage pipeline that (i) estimates network adoption dynamics via a Bayesian dynamic Ising model from a single observed panel, (ii) augments treatment adoption histories with continuous posterior latent states, and (iii) learns a dynamic policy via offline reinforcement learning. The Bayesian mechanism enables uncertainty quantification over dynamic decisions, yielding posterior ensemble policies with interpretable spillover estimates. We provide a finite-sample regret upper bound that decomposes into standard offline-RL uncertainty, network abstraction error, and first stage error in Ising state estimation. We apply our method to data from Indian village microfinance networks and synthetic stochastic block models under simulated heterogeneous susceptible-infected-susceptible (SIS) dynamics and demonstrate that adaptive targeting outperforms static centrality benchmarks.