Timezone: »

Fiduciary Bandits
Gal Bahar · Omer Ben-Porat · Kevin Leyton-Brown · Moshe Tennenholtz

Tue Jul 14 09:00 AM -- 09:45 AM & Tue Jul 14 09:00 PM -- 09:45 PM (PDT) @

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.

Author Information

Gal Bahar (Technion – Israel Institute of Technology)
Omer Ben-Porat (Technion--Israel Institute of Technology)
Kevin Leyton-Brown (University of British Columbia)
Moshe Tennenholtz (Technion – Israel Institute of Technology)

More from the Same Authors