# Fiduciary Bandits

arXiv: https://arxiv.org/abs/1905.07043 · HTML: https://mlsanity.com/paper/1905.07043/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 May 2019.

## Built on by (most cited first, 7 of 7)

- [Modeling Attrition in Recommender Systems with Departing Bandits](https://mlsanity.com/paper/2203.13423/) (2022)
- [Multi-armed Bandit Algorithm against Strategic Replication](https://mlsanity.com/paper/2110.12160/) (2021)
- [Contractual Reinforcement Learning: Pulling Arms with Invisible Hands](https://mlsanity.com/paper/2407.01458/) (2024)
- [Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces](https://mlsanity.com/paper/2306.10606/) (2023)
- [Robust and Performance Incentivizing Algorithms for Multi-Armed Bandits with Strategic Agents](https://mlsanity.com/paper/2312.07929/) (2023)
- [Incentivized Collaboration in Active Learning](https://mlsanity.com/paper/2311.00260/) (2023)
- [On Incentivized Exploration beyond Bayesianism and Full-Information](https://mlsanity.com/paper/2607.18300/) (2026)

## Abstract (arXiv)

Recommendation systems often face exploration-exploitation tradeoffs: the system can only learn about the desirability of new options by recommending them to some user. Such systems can thus be modeled as multi-armed bandit settings; however, users are self-interested and cannot be made to follow recommendations. We ask whether exploration can nevertheless be performed in a way that scrupulously respects agents' interests---i.e., by a system that acts as a fiduciary. More formally, we introduce a model in which a recommendation system faces an exploration-exploitation tradeoff under the constraint that it can never recommend any action that it knows yields lower reward in expectation than an agent would achieve if it acted alone. Our main contribution is a positive result: an asymptotically optimal, incentive compatible, and ex-ante individually rational recommendation algorithm.