Corpus ID: 879579

Normal Bandits of Unknown Means and Variances: Asymptotic Optimality, Finite Horizon Regret Bounds, and a Solution to an Open Problem

@article{Cowan2015NormalBO,
  title={Normal Bandits of Unknown Means and Variances: Asymptotic Optimality, Finite Horizon Regret Bounds, and a Solution to an Open Problem},
  author={Wesley Cowan and M. Katehakis},
  journal={ArXiv},
  year={2015},
  volume={abs/1504.05823}
}
Consider the problem of sampling sequentially from a finite number of N > 2 populations, specified by random variables X i k , i = 1;:::; N; and k = 1; 2;:::; where X i k denotes the outcome from population i the k th time it is sampled. It is assumed that for each fixed i,fX i k gk>1 is a sequence of i.i.d. normal random variables, with unknown mean mi and unknown variance s 2 i . The objective is to have a policy p for deciding from which of the N populations to sample form at any time n = 1… Expand
An Asymptotically Optimal UCB Policy for Uniform Bandits of Unknown Support
Information Directed Sampling and Bandits with Heteroscedastic Noise
Boundary Crossing for General Exponential Families
Asymptotic Behavior of Minimal-Exploration Allocation Policies: Almost Sure, Arbitrarily Slow Growing Regret
ASYMPTOTICALLY OPTIMAL MULTI-ARMED BANDIT POLICIES UNDER A COST CONSTRAINT
I NFORMATION D IRECTED S AMPLING AND B ANDITS WITH
A Scale Free Algorithm for Stochastic Bandits with Bounded Kurtosis
...
1
2
...

References

SHOWING 1-10 OF 48 REFERENCES
An Asymptotically Optimal UCB Policy for Uniform Bandits of Unknown Support
Optimal Adaptive Policies for Sequential Allocation Problems
An Asymptotically Optimal Bandit Algorithm for Bounded Support Models
Optimality of Thompson Sampling for Gaussian Bandits Depends on Priors
Asymptotic Behavior of Minimal-Exploration Allocation Policies: Almost Sure, Arbitrarily Slow Growing Regret
The Multi-Armed Bandit Problem: Decomposition and Computation
ASYMPTOTIC BAYES ANALYSIS FOR THE FINITE-HORIZON ONE-ARMED-BANDIT PROBLEM
On large deviations properties of sequential allocation problems
...
1
2
3
4
5
...