English

On Incentivized Exploration beyond Bayesianism and Full-Information

Computer Science and Game Theory 2026-07-14 v1 Machine Learning

Abstract

We extend Incentive Compatible Exploration beyond the Bayesian full-information setting of Kremer et al. [2014]. We consider agents that may possess external information unknown to the principal. We show such settings require new notions of incentivized exploration, as well as going beyond a Bayesian perspective, and we introduce a definition where agents choose any reasonable (undominated) action. Furthermore, our framework provides for a more robust treatment of ties, and extends to settings where agents lack a single common prior and instead only know that reward distributions belong to a collection of potential priors.

Cite

@article{arxiv.2607.18300,
  title  = {On Incentivized Exploration beyond Bayesianism and Full-Information},
  author = {Dimitar Chakarov and Lee Cohen and Nathan Srebro},
  journal= {arXiv preprint arXiv:2607.18300},
  year   = {2026}
}

Comments

30 pages, 5 figures