Incentivized Exploration via Filtered Posterior Sampling
This addresses the problem of encouraging exploration in recommendation algorithms for sequentially-arriving agents, representing an incremental extension of prior work.
The paper tackles incentivized exploration in social learning by proposing filtered posterior sampling as a solution, expanding its applicability to settings like private agent types and correlated priors while recovering existing results as special cases.
We study "incentivized exploration" (IE) in social learning problems where the principal (a recommendation algorithm) can leverage information asymmetry to incentivize sequentially-arriving agents to take exploratory actions. We identify posterior sampling, an algorithmic approach that is well known in the multi-armed bandits literature, as a general-purpose solution for IE. In particular, we expand the existing scope of IE in several practically-relevant dimensions, from private agent types to informative recommendations to correlated Bayesian priors. We obtain a general analysis of posterior sampling in IE which allows us to subsume these extended settings as corollaries, while also recovering existing results as special cases.