Incentivized Bandit Learning with Self-Reinforcing User Preferences
This addresses a real-world challenge in recommender systems by modeling user incentives and self-reinforcing effects, offering an incremental improvement to existing bandit frameworks.
The paper tackles the problem of incentivized bandit learning where an agent must offer rewards to users to indirectly pull arms, while users' self-reinforcing preferences affect outcomes, aiming to maximize total reward with low payment over time T. It proposes two policies that achieve O(log T) expected regret and payment, as verified through simulations.
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.