Learning the distribution with largest mean: two bandit frameworks
arXiv:1702.00001
Abstract
Over the past few years, the multi-armed bandit model has become increasingly popular in the machine learning community, partly because of applications including online content optimization. This paper reviews two different sequential learning tasks that have been considered in the bandit literature ; they can be formulated as (sequentially) learning which distribution has the highest mean among a set of distributions, with some constraints on the learning process. For both of them (regret minimization and best arm identification) we present recent, asymptotically optimal algorithms. We compare the behaviors of the sampling rule of each algorithm as well as the complexity terms associated to each problem.
References in corpus (8)
- Further Optimal Regret Bounds for Thompson Sampling
- lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits
- Batched bandit problems
- Lipschitz Bandits: Regret Lower Bounds and Optimal Algorithms
- Thompson Sampling: An Asymptotically Optimal Finite Time Analysis
- Towards Instance Optimal Bounds for Best Arm Identification
- Unimodal Bandits without Smoothness
- On the Complexity of A/B Testing