On the Optimal Amount of Experimentation in Sequential Decision Problems

2009/07/12 by Dinah Rosenberg, Rosenberg, Dinah, Eilon Solan +3
Mathematics · #60G99 #62C10 #93E35 #FOS: Mathematics #Probability (math.PR) #Statistics Theory (math.ST) #math.PR #math.ST #msc:60G99 #msc:62C10 #msc:93E35 #stat.TH

paper · pdf · doi:10.48550/arxiv.0907.2002

arxiv created 2009/07/12 · arxiv updated 2009/12/01

Abstract

We provide a tight bound on the amount of experimentation under the optimal strategy in sequential decision problems. We show the applicability of the result by providing a bound on the cut-off in a one-arm bandit problem.

Related

• Optimal tests following sequential experiments
• Double Explore-then-Commit: Asymptotic Optimality and Beyond
• Sequential Design of Experiments via Linear Programming
• Approximate optimality and the risk/reward tradeoff in a class of bandit problems
• Sequential Multi-hypothesis Testing in Multi-armed Bandit Problems:An Approach for Asymptotic Optimality