Incentivized Exploration via Filtered Posterior Sampling
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913238369697792 |
|---|---|
| author | Kalvit, Anand Slivkins, Aleksandrs Gur, Yonatan |
| author_facet | Kalvit, Anand Slivkins, Aleksandrs Gur, Yonatan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13338 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Incentivized Exploration via Filtered Posterior Sampling Kalvit, Anand Slivkins, Aleksandrs Gur, Yonatan Machine Learning Theoretical Economics 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. |
| title | Incentivized Exploration via Filtered Posterior Sampling |
| topic | Machine Learning Theoretical Economics |
| url | https://arxiv.org/abs/2402.13338 |