Bayesian incentive-compatible bandit exploration

Yishay Mansour, Aleksandrs Slivkins, Vasilis Syrgkanis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Individual decision-makers consume information revealed by the previous decision makers, and produce information that may help in future decision makers. This phenomenon is common in a wide range of sce- narios in the Internet economy, as well as elsewhere, such as medical decisions. Each decision maker when required to select an action, would individually prefer to exploit, select the highest expected reward ac- tion conditional on her information. At the same time, each decision maker would prefer previous decision makers to explore, producing information about the rewards of various actions. A social planner, by means of carefully designed information disclosure, can incentivize the agents to balance the exploration and ex- ploitation, and maximize social welfare. We formulate this problem as a multi-arm bandit problem (and various generalizations thereof) under incentive-compatibility constraints induced by agents' Bayesian priors. We design an incentive-compatible bandit algorithm for the social planner with asymptotically optimal regret. Further, we provide a black- box reduction from an arbitrary multi-arm bandit algorithm to an incentive-compatible one, with only a constant multiplicative increase in regret. This reduction works for very general bandit settings, even ones that incorporate contexts and arbitrary partial feedback.

Original languageEnglish
Title of host publicationEC 2015 - Proceedings of the 2015 ACM Conference on Economics and Computation
Number of pages18
ISBN (Electronic)9781450334105
StatePublished - 15 Jun 2015
Event16th ACM Conference on Economics and Computation, EC 2015 - Portland, United States
Duration: 15 Jun 201519 Jun 2015

Publication series

NameEC 2015 - Proceedings of the 2015 ACM Conference on Economics and Computation


Conference16th ACM Conference on Economics and Computation, EC 2015
Country/TerritoryUnited States


  • Bayesian incentive-compatibility
  • Mechanism design
  • Multi-armed bandits
  • Regret

All Science Journal Classification (ASJC) codes

  • Economics and Econometrics
  • Statistics and Probability
  • Computer Science (miscellaneous)
  • Computational Mathematics
  • Marketing


Dive into the research topics of 'Bayesian incentive-compatible bandit exploration'. Together they form a unique fingerprint.

Cite this