# Combinatorial Bandits for Incentivizing Agents with Dynamic Preferences

arXiv: https://arxiv.org/abs/1807.02297 · HTML: https://mlsanity.com/paper/1807.02297/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2018.

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

- [Principal-Agent Bandit Games with Self-Interested and Exploratory Learning Agents](https://mlsanity.com/paper/2412.16318/) (2024)
- [Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals](https://mlsanity.com/paper/2505.23124/) (2025)

## Abstract (arXiv)

The design of personalized incentives or recommendations to improve user engagement is gaining prominence as digital platform providers continually emerge. We propose a multi-armed bandit framework for matching incentives to users, whose preferences are unknown a priori and evolving dynamically in time, in a resource constrained environment. We design an algorithm that combines ideas from three distinct domains: (i) a greedy matching paradigm, (ii) the upper confidence bound algorithm (UCB) for bandits, and (iii) mixing times from the theory of Markov chains. For this algorithm, we provide theoretical bounds on the regret and demonstrate its performance via both synthetic and realistic (matching supply and demand in a bike-sharing platform) examples.