# Incentivized Bandit Learning with Self-Reinforcing User Preferences

arXiv: https://arxiv.org/abs/2105.08869 · HTML: https://mlsanity.com/paper/2105.08869/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 39 references that are in the map.
- First posted on arXiv 19 May 2021.

## Builds on (most cited first, 8 of 8)

- [Bayesian Incentive-Compatible Bandit Exploration](https://mlsanity.com/paper/1502.04147/) (2015)
- [A Survey on Practical Applications of Multi-Armed and Contextual Bandits](https://mlsanity.com/paper/1904.10040/) (2019)
- [Bayesian Exploration: Incentivizing Exploration in Bayesian Games](https://mlsanity.com/paper/1602.07570/) (2016)
- [Thompson Sampling for Budgeted Multi-armed Bandits](https://mlsanity.com/paper/1505.00146/) (2015)
- [Multi-armed Bandits with Compensation](https://mlsanity.com/paper/1811.01715/) (2018)
- [Bandit Learning with Positive Externalities](https://mlsanity.com/paper/1802.05693/) (2018)
- [Multi-Armed Bandits for Correlated Markovian Environments with Smoothed Reward Feedback](https://mlsanity.com/paper/1803.04008/) (2018)
- [Incentivising Exploration and Recommendations for Contextual Bandits with Payments](https://mlsanity.com/paper/2001.07853/) (2020)

## Built on by (most cited first, 2 of 2)

- [Online Recommendations for Agents with Discounted Adaptive Preferences](https://mlsanity.com/paper/2302.06014/) (2023)
- [Socially-Optimal Mechanism Design for Incentivized Online Learning](https://mlsanity.com/paper/2112.14338/) (2021)

## Abstract (arXiv)

In this paper, we investigate a new multi-armed bandit (MAB) online learning model that considers real-world phenomena in many recommender systems: (i) the learning agent cannot pull the arms by itself and thus has to offer rewards to users to incentivize arm-pulling indirectly; and (ii) if users with specific arm preferences are well rewarded, they induce a "self-reinforcing" effect in the sense that they will attract more users of similar arm preferences. Besides addressing the tradeoff of exploration and exploitation, another key feature of this new MAB model is to balance reward and incentivizing payment. The goal of the agent is to maximize the total reward over a fixed time horizon T with a low total payment. Our contributions in this paper are two-fold: (i) We propose a new MAB model with random arm selection that considers the relationship of users' self-reinforcing preferences and incentives; and (ii) We leverage the properties of a multi-color Polya urn with nonlinear feedback model to propose two MAB policies termed "At-Least-n Explore-Then-Commit" and "UCB-List". We prove that both policies achieve O(log T) expected regret with O(log T) expected payment over a time horizon T. We conduct numerical simulations to demonstrate and verify the performances of these two policies and study their robustness under various settings.