References

• 2002Finite-time Analysis of the Multiarmed Bandit Problem5,980 cited
• 1952Some aspects of the sequential design of experiments2,183 cited
• 2012Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting2,098 cited
• 1979Bandit Processes and Dynamic Allocation Indices1,488 cited
• 2011Online Learning and Online Convex Optimization1,095 cited
• 2011An Empirical Evaluation of Thompson Sampling1,000 cited
• 2011Analysis of Thompson Sampling for the multi-armed bandit problem904 cited
• 2011Improved Algorithms for Linear Stochastic Bandits860 cited
• 1997Exponentiated Gradient versus Gradient Descent for Linear Predictors856 cited
• 2010Near-optimal Regret Bounds for Reinforcement Learning718 cited
• 2008Stochastic Linear Optimization Under Bandit Feedback581 cited
• 2010Linearly Parameterized Bandits428 cited
• 2008Multi-armed bandits in metric spaces353 cited
• 2002PAC Bounds for Multi-armed Bandit and Markov Decision Processes300 cited
• 2004Nearly Tight Bounds for the Continuum-Armed Bandit Problem285 cited
• 2001Competitive On‐line Statistics