Bayesian Incentive-Compatible Bandit Exploration

DOI10.1287/opre.2019.1949zbMath1451.90079arXiv1502.04147OpenAlexW3038752685MaRDI QIDQ3387959

Aleksandrs Slivkins, Yishay Mansour, Vasilis Syrgkanis

Publication date: 8 January 2021

Published in: Operations Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1502.04147

zbMATH Keywords

mechanism designregretmultiarmed banditsBayesian incentive-compatibility

Mathematics Subject Classification ID

Management decision making, including multiple objectives (90B50)

Related Items (7)

The platform design problem ⋮ Bayesian Exploration: Incentivizing Exploration in Bayesian Games ⋮ Regret minimization in online Bayesian persuasion: handling adversarial receiver's types under full and partial feedback models ⋮ Optimal and Efficient Auctions for the Gradual Procurement of Strategic Service Provider Agents ⋮ Budget-constrained cost-covering job assignment for a total contribution-maximizing platform ⋮ On the hardness of designing public signals ⋮ Algorithmic Bayesian Persuasion

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Asymptotically efficient adaptive allocation rules
• Pure exploration in finitely-armed and continuous-armed bandits
• Truthful Mechanisms with Implicit Payment Computation
• Fairness through awareness
• Learning and incentives in user-generated content
• Monitoring Clinical Trials with Multiple Arms
• Multi‐Armed Bandit Allocation Indices
• Dynamic Pricing Without Knowing the Demand Function: Risk Bounds and Near-Optimal Algorithms
• Adaptive Contract Design for Crowdsourcing Markets: Bandit Algorithms for Repeated Principal-Agent Problems
• The Dynamic Pivot Mechanism
• A One-Armed Bandit Problem with a Concomitant Variable
• Strategic Experimentation
• Bandits with Knapsacks
• The Nonstochastic Multiarmed Bandit Problem
• Optimal Dynamic Mechanism Design and the Virtual-Pivot Mechanism
• Partial Monitoring—Classification, Regret Bounds, and Algorithms
• Bandit problems with side observations
• Probability Inequalities for Sums of Bounded Random Variables
• Strategic Experimentation with Exponential Bandits
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• An Efficient Dynamic Mechanism
• Characterizing Truthful Multi-armed Bandit Mechanisms
• Probability and Computing
• Prediction, Learning, and Games
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Bayesian Incentive-Compatible Bandit Exploration