An incentive-compatible multi-armed bandit mechanism

DOI10.1145/1281100.1281174MaRDI QIDQ5401464zbMATH OpenOpenAlexFDO

Authors Rica Gonen, Elan Pavlov

Publication date 13 March 2014

Published in Proceedings of the twenty-sixth annual ACM symposium on Principles of distributed computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1145/1281100.1281174

zbMATH Keywords

multi-armed bandittruthfulincentive compatible

Mathematics Subject Classification ID

Auctions, bargaining, bidding and selling, and other market models (91B26) Probabilistic games; gambling (91A60)

Recommendations

• Bayesian Incentive-Compatible Bandit Exploration
• Satisficing in Multi-Armed Bandit Problems
• Multi-armed bandit with sub-exponential rewards
• A Structured Multiarmed Bandit Problem and the Greedy Policy
• Characterizing Truthful Multi-armed Bandit Mechanisms
• Combinatorial multi-armed bandit and its extension to probabilistically triggered arms
• Multi-armed bandit problem revisited
• The Nonstochastic Multiarmed Bandit Problem
• Multi-armed bandits in discrete and continuous time

Cited in

(7)

• Mechanisms with learning for stochastic multi-armed bandit problems
• Maintaining equilibria during exploration in sponsored search auctions
• A penalized bandit algorithm
• Characterizing Truthful Multi-armed Bandit Mechanisms
• The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity
• Learning and incentives in user-generated content: multi-armed bandits with endogenous arms
• Truthful learning mechanisms for multi-slot sponsored search auctions with externalities

This page was built for publication: An incentive-compatible multi-armed bandit mechanism

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5401464)