2 papers
cs.LG2024
Incentivized Exploration via Filtered Posterior Sampling
Anand Kalvit, Aleksandrs Slivkins, Yonatan Gur
We study "incentivized exploration" (IE) in social learning problems where the principal (a recommendation algorithm) can leverage information asymmetry to incentivize sequentially…
cs.LG2023
Complexity Analysis of a Countable-armed Bandit Problem
Anand Kalvit, Assaf Zeevi
We consider a stochastic multi-armed bandit (MAB) problem motivated by ``large'' action spaces, and endowed with a population of arms containing exactly arm-types, each charact…