# Regularized Contextual Bandits

arXiv: https://arxiv.org/abs/1810.05065 · HTML: https://mlsanity.com/paper/1810.05065/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Oct 2018.

## Built on by (most cited first, 4 of 4)

- [Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits](https://mlsanity.com/paper/2110.09133/) (2021)
- [KL-regularization Itself is Differentially Private in Bandits and RLHF](https://mlsanity.com/paper/2505.18407/) (2025)
- [Necessary and Sufficient Conditions for Inverse Reinforcement Learning of Bayesian Stopping Time Problems](https://mlsanity.com/paper/2007.03481/) (2020)
- [Entropy Regularization for Population Estimation](https://mlsanity.com/paper/2208.11747/) (2022)

## Abstract (arXiv)

We consider the stochastic contextual bandit problem with additional regularization. The motivation comes from problems where the policy of the agent must be close to some baseline policy which is known to perform well on the task. To tackle this problem we use a nonparametric model and propose an algorithm splitting the context space into bins, and solving simultaneously - and independently - regularized multi-armed bandit instances on each bin. We derive slow and fast rates of convergence, depending on the unknown complexity of the problem. We also consider a new relevant margin condition to get problem-independent convergence rates, ending up in intermediate convergence rates interpolating between the aforementioned slow and fast rates.