Pure exploration in finitely-armed and continuous-armed bandits

2010/12/29 by Sébastien Bubeck, Rémi Munos, Gilles Stoltz · 10 citations
Decision Sciences · Computer Science · #Advanced Bandit Algorithms Research #Reinforcement Learning in Robotics #Auction Theory and Applications

paper · doi:10.1016/j.tcs.2010.12.059

Citations

• The Nonstochastic Multiarmed Bandit Problem
• Probability Inequalities for Sums of Bounded Random Variables

Cited by

• Short-Term Pain for Long-Term Gain: Adaptive Experiment with Post-Commitment Reward Shift
• Minimax and Bayes Optimal Adaptive Experimental Design for Treatment Choice
• On Multi-Armed Bandit Designs for Dose-Finding Clinical Trials
• On the Complexity of Bandit and Derivative-Free Stochastic Convex\n Optimization
• Selecting Computations: Theory and Applications
• Optimal Best-Arm Identification Methods for Tail-Risk Measures
• Bandits with many optimal arms
• DyBBT: Dynamic Balance via Bandit inspired Targeting for Dialog Policy with Cognitive Dual-Systems
• Search as Computation Allocation
• The Role of Contextual Information in Best Arm Identification