# Action Centered Contextual Bandits

arXiv: https://arxiv.org/abs/1711.03596 · HTML: https://mlsanity.com/paper/1711.03596/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2017.

## Built on by (most cited first, 23 of 23)

- [Federated Neural Bandits](https://mlsanity.com/paper/2205.14309/) (2022)
- [Efficient Online Bayesian Inference for Neural Bandits](https://mlsanity.com/paper/2112.00195/) (2021)
- [Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Model](https://mlsanity.com/paper/1901.11221/) (2019)
- [Regret Distribution in Stochastic Bandits: Optimal Trade-off between Expectation and Tail Risk](https://mlsanity.com/paper/2304.04341/) (2023)
- [Efficient Inference Without Trading-off Regret in Bandits: An Allocation Probability Test for Thompson Sampling](https://mlsanity.com/paper/2111.00137/) (2021)
- [Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions](https://mlsanity.com/paper/2203.02605/) (2022)
- [reBandit: Random Effects based Online RL algorithm for Reducing Cannabis Use](https://mlsanity.com/paper/2402.17739/) (2024)
- [RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health Interventions](https://mlsanity.com/paper/2312.06403/) (2023)
- [Semi-Parametric Contextual Bandits with Graph-Laplacian Regularization](https://mlsanity.com/paper/2205.08295/) (2022)
- [Thompson sampling for zero-inflated count outcomes with an application to the Drink Less mobile health study](https://mlsanity.com/paper/2311.14359/) (2023)
- [MiWaves Reinforcement Learning Algorithm](https://mlsanity.com/paper/2408.15076/) (2024)
- [Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect Oracles](https://mlsanity.com/paper/2203.16668/) (2022)
- [GBOSE: Generalized Bandit Orthogonalized Semiparametric Estimation](https://mlsanity.com/paper/2301.08781/) (2023)
- [Active and Passive Causal Inference Learning](https://mlsanity.com/paper/2308.09248/) (2023)
- [Effective Monitoring of Online Decision-Making Algorithms in Digital Intervention Implementation](https://mlsanity.com/paper/2409.10526/) (2024)
- [Tangential Randomization in Linear Bandits (TRAiL): Guaranteed Inference and Regret Bounds](https://mlsanity.com/paper/2411.12154/) (2024)
- [Experimental Design for Semiparametric Bandits](https://mlsanity.com/paper/2506.13390/) (2025)
- [Adaptive Interventions with User-Defined Goals for Health Behavior Change](https://mlsanity.com/paper/2311.09483/) (2023)
- [Artificial Intelligence-based Decision Support Systems for Precision and Digital Health](https://mlsanity.com/paper/2407.16062/) (2024)
- [Nearly Optimal Best Arm Identification for Semiparametric Bandits](https://mlsanity.com/paper/2604.03969/) (2026)
- [Personalizing Large Language Model Agents with Small Policy Models](https://mlsanity.com/paper/2608.00215/) (2026)
- [Posterior Tempering Explains Variance Inflation in Linear and Generalized Linear Thompson Sampling](https://mlsanity.com/paper/2609.01999/) (2026)
- [Odds-Ratio Thompson Sampling: A Specification and Design Guide for Contrast-Based Multi-Armed Bandits](https://mlsanity.com/paper/2609.19709/) (2026)

## Abstract (arXiv)

Contextual bandits have become popular as they offer a middle ground between very simple approaches based on multi-armed bandits and very complex approaches using the full power of reinforcement learning. They have demonstrated success in web applications and have a rich body of associated theoretical guarantees. Linear models are well understood theoretically and preferred by practitioners because they are not only easily interpretable but also simple to implement and debug. Furthermore, if the linear model is true, we get very strong performance guarantees. Unfortunately, in emerging applications in mobile health, the time-invariant linear model assumption is untenable. We provide an extension of the linear model for contextual bandits that has two parts: baseline reward and treatment effect. We allow the former to be complex but keep the latter simple. We argue that this model is plausible for mobile health applications. At the same time, it leads to algorithms with strong performance guarantees as in the linear model setting, while still allowing for complex nonlinear baseline modeling. Our theory is supported by experiments on data gathered in a recently concluded mobile health study.